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

    Neuronpedia

    INDEX
    Explanations

    Math proofs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     réseau
    -0.06
     मर
    -0.06
    uvian
    -0.06
     Cabr
    -0.06
     starting
    -0.06
    ौकर
    -0.06
     commit
    -0.06
     Corpor
    -0.06
    )))),
    -0.06
     одерж
    -0.06
    POSITIVE LOGITS
     kvinna
    0.08
    ––
    0.07
    .Script
    0.06
    (stream
    0.06
    .TR
    0.06
     humiliation
    0.06
    (texture
    0.06
    TouchUpInside
    0.06
    のか
    0.06
     shocking
    0.06
    Act Density 0.114%

    No Known Activations