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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    )_
    -0.07
     pojištění
    -0.06
    =_
    -0.06
     NSTextAlignment
    -0.06
    ิส
    -0.06
     �
    -0.06
     tě
    -0.06
    _migration
    -0.06
     semester
    -0.06
     wines
    -0.06
    POSITIVE LOGITS
    .slider
    0.07
    务
    0.07
    !");↵↵
    0.07
     assemble
    0.06
     hashlib
    0.06
    .…↵↵
    0.06
    ër
    0.06
    !↵↵↵↵
    0.06
    [out
    0.06
     вспом
    0.06
    Act Density 0.048%

    No Known Activations