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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    list
    -0.07
     launch
    -0.07
     economies
    -0.07
     NL
    -0.07
    ottle
    -0.07
    -ups
    -0.07
    Subscription
    -0.06
     networks
    -0.06
    -school
    -0.06
    比赛
    -0.06
    POSITIVE LOGITS
     humid
    0.06
     cerebral
    0.06
    ・・・
    0.06
    wig
    0.06
    deki
    0.06
     العم
    0.06
     формы
    0.06
    형
    0.06
     cine
    0.06
     限
    0.06
    Act Density 0.042%

    No Known Activations