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

    Neuronpedia

    INDEX
    Explanations

    nach

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     elit
    -0.07
    INS
    -0.07
    fidf
    -0.07
    รวม
    -0.07
     biom
    -0.06
    apiro
    -0.06
     Ion
    -0.06
     Miller
    -0.06
    yi
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     wait
    0.06
    (annotation
    0.06
    otent
    0.06
    ضاء
    0.06
     add
    0.06
     brackets
    0.06
    confirmation
    0.06
    ‐‐
    0.06
    _dashboard
    0.06
     underwent
    0.06
    Act Density 0.004%

    No Known Activations