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
    lfw
    -0.07
    .position
    -0.07
     길
    -0.07
    //================================================
    -0.06
    (ap
    -0.06
    quential
    -0.06
     economical
    -0.06
     Half
    -0.06
     đem
    -0.06
    _wind
    -0.06
    POSITIVE LOGITS
    sects
    0.07
     będ
    0.06
     pinpoint
    0.06
    �
    0.06
    ordering
    0.06
    чень
    0.06
    >Action
    0.06
     unserem
    0.06
    /url
    0.06
    stri
    0.06
    Act Density 0.012%

    No Known Activations