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

    Neuronpedia

    INDEX
    Explanations

    Before acting or deciding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pager
    -0.08
    Weather
    -0.07
    ’à
    -0.07
    Samsung
    -0.07
    šetření
    -0.07
    іл
    -0.07
    .getKey
    -0.06
    icích
    -0.06
    [selected
    -0.06
    weights
    -0.06
    POSITIVE LOGITS
     Equ
    0.07
     Clinic
    0.06
     LABEL
    0.06
    CERT
    0.06
    arParams
    0.06
     suburb
    0.06
     وكانت
    0.06
     договору
    0.06
     代
    0.06
     dictator
    0.05
    Act Density 0.046%

    No Known Activations