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

    Neuronpedia

    INDEX
    Explanations

    delivered opinion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ビー
    -0.06
    lates
    -0.06
    _-_
    -0.06
    Stopping
    -0.06
    [offset
    -0.06
    _chr
    -0.06
    ALI
    -0.06
    ैन
    -0.06
    半
    -0.06
    imagin
    -0.06
    POSITIVE LOGITS
    _inverse
    0.07
     transactions
    0.06
    _publish
    0.06
     horizon
    0.06
    ivist
    0.06
     incess
    0.06
     sle
    0.06
     temas
    0.06
    ***↵↵
    0.06
     pronounced
    0.06
    Act Density 0.087%

    No Known Activations