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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     robbery
    -0.07
     Fatal
    -0.07
     customers
    -0.07
     scenarios
    -0.06
    ="?
    -0.06
    _alias
    -0.06
     نمودار
    -0.06
     property
    -0.06
    _shell
    -0.06
    λ
    -0.06
    POSITIVE LOGITS
    InMillis
    0.07
    mít
    0.07
     sopr
    0.06
    isses
    0.06
     İmparator
    0.06
    73
    0.06
    _DISCONNECT
    0.06
    DSP
    0.06
    xmin
    0.06
     disarm
    0.06
    Act Density 0.047%

    No Known Activations