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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    た
    -0.07
    ysl
    -0.06
    stery
    -0.06
    وي
    -0.06
    严
    -0.06
    during
    -0.06
     doit
    -0.06
    _Draw
    -0.06
    layer
    -0.06
    plt
    -0.06
    POSITIVE LOGITS
    HomeAsUp
    0.07
     Joey
    0.06
     Unsigned
    0.06
    ]-$
    0.06
     downstairs
    0.06
    $arity
    0.06
     glitch
    0.06
    -null
    0.06
     welfare
    0.06
     Refuge
    0.06
    Act Density 0.005%

    No Known Activations