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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "New"

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

    New York and Mexico

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    featureID
    -0.68
     Italijani
    -0.52
     typelib
    -0.48
     ब्रेकडाउन
    -0.46
     duquel
    -0.44
    bcryptjs
    -0.44
     Lordships
    -0.43
    AnimationsModule
    -0.43
    abestanden
    -0.42
    aderie
    -0.41
    POSITIVE LOGITS
     New
    0.97
    New
    0.67
     न्यू
    0.56
     뉴
    0.56
     ニュー
    0.54
     Nueva
    0.53
     York
    0.51
     National
    0.50
     Black
    0.48
     San
    0.48
    Act Density 0.012%

    No Known Activations