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

    Neuronpedia

    INDEX
    Explanations

    statistics/odds ratios

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     opc
    -0.07
     ولك
    -0.07
     mettre
    -0.07
    -have
    -0.07
     Coleman
    -0.07
     Invite
    -0.07
    не
    -0.06
    昧
    -0.06
     nga
    -0.06
    Exited
    -0.06
    POSITIVE LOGITS
     ello
    0.07
    предел
    0.07
    沉重
    0.07
    راتيج
    0.07
    OTP
    0.07
     unpredict
    0.07
     Interval
    0.07
     Goals
    0.07
    엿
    0.07
    スピード
    0.07
    Act Density 0.011%

    No Known Activations