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

    Neuronpedia

    INDEX
    Explanations

    established

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rampant
    -0.07
    ationToken
    -0.06
     ironic
    -0.06
    аних
    -0.06
     Hand
    -0.06
     stap
    -0.06
     Password
    -0.06
     películ
    -0.06
    ookeeper
    -0.06
     overrides
    -0.06
    POSITIVE LOGITS
    IRQ
    0.07
    _stdio
    0.07
     MARK
    0.06
     asbestos
    0.06
     Hải
    0.06
     Detected
    0.06
    Stopping
    0.06
     Да
    0.06
    .obj
    0.06
    ryptography
    0.06
    Act Density 0.012%

    No Known Activations