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

    Neuronpedia

    INDEX
    Explanations

    Code/Programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .sensor
    -0.07
     Ge
    -0.07
    arked
    -0.06
    icies
    -0.06
     ic
    -0.06
    をご
    -0.06
     percentile
    -0.06
    .prod
    -0.06
    馇
    -0.06
    urtles
    -0.06
    POSITIVE LOGITS
    _hit
    0.09
     التنفيذي
    0.08
     consulting
    0.07
     defending
    0.07
    ;↵↵
    0.07
    joining
    0.07
    (norm
    0.07
    占领
    0.07
     成
    0.07
     CNC
    0.07
    Act Density 0.756%

    No Known Activations