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
     factual
    -0.07
    matcher
    -0.06
    sl
    -0.06
     alleles
    -0.06
     detach
    -0.06
    าซ
    -0.06
    _rel
    -0.06
    assword
    -0.06
    indle
    -0.06
    358
    -0.06
    POSITIVE LOGITS
    ový
    0.07
     Intermediate
    0.07
     BAR
    0.07
    kový
    0.07
    /debug
    0.06
    TEX
    0.06
     ApiController
    0.06
     originally
    0.06
    ева
    0.06
     Fresh
    0.06
    Act Density 0.015%

    No Known Activations