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

    Neuronpedia

    INDEX
    Explanations

    4

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     compens
    -0.07
    .Player
    -0.07
     Lockheed
    -0.06
     allerg
    -0.06
     функци
    -0.06
    285
    -0.06
    $rs
    -0.06
    taskId
    -0.06
     SSH
    -0.06
     infiltration
    -0.06
    POSITIVE LOGITS
     �
    0.07
     murdered
    0.06
    izo
    0.06
    랫
    0.06
     SEXP
    0.06
     assures
    0.06
    품
    0.06
    _nav
    0.06
     HEALTH
    0.06
     to
    0.06
    Act Density 0.018%

    No Known Activations