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

    Neuronpedia

    INDEX
    Explanations

    punctuation, code, unstructured data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     articulate
    -0.07
    umd
    -0.07
     grav
    -0.07
     crosses
    -0.07
    ixedReality
    -0.06
    _vocab
    -0.06
     allot
    -0.06
     gå
    -0.06
     zemi
    -0.06
    asmus
    -0.06
    POSITIVE LOGITS
     poultry
    0.07
    /php
    0.07
     Hulk
    0.07
    assign
    0.06
     sadness
    0.06
    /signup
    0.06
     thriller
    0.06
     listings
    0.06
    actical
    0.06
    รงเร
    0.06
    Act Density 0.000%

    No Known Activations