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

    Neuronpedia

    INDEX
    Explanations

    This

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    !";
    0.52
    }$=
    0.52
    嚨
    0.49
    都不
    0.48
    都会
    0.48
    都會
    0.48
    ToExp
    0.46
    !;
    0.46
    都沒有
    0.46
    UserName
    0.45
    POSITIVE LOGITS
     includes
    0.99
     contrasts
    0.94
     differs
    0.86
     culminates
    0.84
     contributes
    0.81
     necessitates
    0.80
     makes
    0.80
     means
    0.80
     happens
    0.79
    includes
    0.77
    Act Density 0.235%

    No Known Activations