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

    Neuronpedia

    INDEX
    Explanations

    Arbitrary mixed text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     representation
    -0.08
    /screens
    -0.07
     respectively
    -0.07
    .dim
    -0.07
     manipulation
    -0.06
    _int
    -0.06
    ैं।↵↵
    -0.06
    .proxy
    -0.06
     Measures
    -0.06
     integral
    -0.06
    POSITIVE LOGITS
     　　 　
    0.07
    たし
    0.06
    ادث
    0.06
    ▲
    0.06
    停
    0.06
    ätz
    0.06
    :r
    0.06
     Zig
    0.06
     Patrol
    0.06
    0.06
    Act Density 0.000%

    No Known Activations