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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate physical actions or movements

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

    prepositions indicating position or state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tartalomajánló
    -0.51
     port
    -0.39
     tab
    -0.38
     hare
    -0.38
     georg
    -0.38
     registration
    -0.37
     rodriguez
    -0.37
     series
    -0.36
     position
    -0.36
     devices
    -0.36
    POSITIVE LOGITS
    ConstraintMaker
    0.71
    期刊论文
    0.63
     CreateTagHelper
    0.62
     féminine
    0.62
     ilustracji
    0.60
     personnalisée
    0.59
     srdce
    0.59
    AndEndTag
    0.57
     vectorielle
    0.55
     continúas
    0.55
    Act Density 0.024%

    No Known Activations