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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PV
    -0.08
    brane
    -0.07
    Grant
    -0.07
     tab
    -0.06
    procedure
    -0.06
    _op
    -0.06
    _db
    -0.06
    .service
    -0.06
     posterior
    -0.06
     spectacular
    -0.06
    POSITIVE LOGITS
    /docs
    0.07
    ㅠㅠ
    0.07
     sscanf
    0.06
    RETURN
    0.06
    ouncill
    0.06
    erator
    0.06
     documento
    0.06
     Weston
    0.06
     dafür
    0.06
     downturn
    0.06
    Act Density 0.024%

    No Known Activations