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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating types or categories of things

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

    Follows "of the" or "the [adjective]"

    np_acts-logits-general · gemini-2.0-flash

    identifying kinds of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jegy
    -0.55
     européennes
    -0.53
     commerciales
    -0.52
     llorar
    -0.51
     féminine
    -0.50
     nationales
    -0.50
     colpa
    -0.48
     nationaux
    -0.48
     étrangères
    -0.47
     jambes
    -0.47
    POSITIVE LOGITS
     CreateTagHelper
    0.86
    setVerticalGroup
    0.81
    awtextra
    0.76
    findpost
    0.75
    رشف
    0.74
    Obrázky
    0.71
     havoc
    0.71
     way
    0.69
    EndInit
    0.69
    lismo
    0.68
    Act Density 0.247%

    No Known Activations