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

    Neuronpedia

    INDEX
    Explanations

    code files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nacional
    -0.06
    _while
    -0.06
    int
    -0.06
     нерв
    -0.06
    нулся
    -0.06
    centers
    -0.06
    Immutable
    -0.06
     vida
    -0.06
     TLC
    -0.06
    urrent
    -0.06
    POSITIVE LOGITS
    .Has
    0.07
     Prepare
    0.06
     speak
    0.06
     servings
    0.06
    vů
    0.06
    ('/:
    0.06
     craft
    0.06
    _debug
    0.06
    /?
    0.06
    Batch
    0.06
    Act Density 0.000%

    No Known Activations