Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    forms of the verb "to be" and related variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "are" followed by a verb ending in "ing"

    np_acts-logits-general · gemini-2.0-flash

    states and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.66
    makeConstraints
    -0.61
    Xna
    -0.60
     NSCoder
    -0.54
    ArgsConstructor
    -0.53
     kanyang
    -0.53
     bağlantılar
    -0.52
    Demografie
    -0.52
     OnClickListener
    -0.51
    InputTagHelper
    -0.49
    POSITIVE LOGITS
     residing
    0.64
     married
    0.63
     living
    0.63
     planning
    0.60
     senior
    0.58
    vician
    0.56
     interested
    0.55
     enrolled
    0.55
     trained
    0.54
     female
    0.54
    Act Density 0.308%

    No Known Activations