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

    Neuronpedia

    INDEX
    Explanations

    technical documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     event
    -0.07
    Ð
    -0.06
    secutive
    -0.06
     confidential
    -0.06
    _Client
    -0.06
    >v
    -0.06
     cortex
    -0.06
    mdat
    -0.06
    matching
    -0.06
    kk
    -0.06
    POSITIVE LOGITS
     Virgin
    0.07
    （笑
    0.07
    ńst
    0.06
     شن
    0.06
    Sharp
    0.06
     Schultz
    0.06
    243
    0.06
    July
    0.06
    _CD
    0.06
    Feb
    0.06
    Act Density 0.000%

    No Known Activations