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

    Neuronpedia

    INDEX
    Explanations

    Proximity/approximation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    utow
    -0.06
    894
    -0.06
    ोख
    -0.06
    rdf
    -0.06
    _b
    -0.06
    umont
    -0.06
    SQ
    -0.06
    365
    -0.06
     재
    -0.06
    Di
    -0.06
    POSITIVE LOGITS
     proficient
    0.07
    /shared
    0.07
    steller
    0.06
    .Category
    0.06
     surprising
    0.06
    (nn
    0.06
    chunks
    0.06
     prostitution
    0.06
     есте
    0.06
     strengthens
    0.06
    Act Density 0.019%

    No Known Activations