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

    Neuronpedia

    INDEX
    Explanations

    Article excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pissed
    -0.07
    istani
    -0.07
    じゃ
    -0.07
    round
    -0.07
    Rick
    -0.07
     Open
    -0.07
    显现
    -0.07
    热爱
    -0.07
     zoom
    -0.07
    rides
    -0.06
    POSITIVE LOGITS
     MART
    0.07
     rapidement
    0.07
    (binary
    0.07
     Ба
    0.06
    Saga
    0.06
     SCT
    0.06
    _ACTIVITY
    0.06
     Felipe
    0.06
     TTC
    0.06
    ילת
    0.06
    Act Density 0.284%

    No Known Activations