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

    Neuronpedia

    INDEX
    Explanations

    expect

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Geb
    -0.06
    nám
    -0.06
    adapt
    -0.06
    BI
    -0.06
    Century
    -0.06
    칠
    -0.06
    onclick
    -0.06
    桑
    -0.06
    bast
    -0.06
    enne
    -0.06
    POSITIVE LOGITS
     scanner
    0.07
     moderation
    0.07
    .process
    0.07
    ंतर
    0.06
    _access
    0.06
    _MINUS
    0.06
    Deferred
    0.06
    .Property
    0.06
    	assertTrue
    0.06
     certainly
    0.06
    Act Density 0.003%

    No Known Activations