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

    Neuronpedia

    INDEX
    Explanations

    magazines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rubble
    -0.07
     Suicide
    -0.07
     lemon
    -0.07
    ################################################
    -0.06
    .getIn
    -0.06
     dialogs
    -0.06
     Rib
    -0.06
    ','',
    -0.06
    ucks
    -0.06
     twins
    -0.06
    POSITIVE LOGITS
    면서
    0.08
    ňuje
    0.07
    sale
    0.07
     незалеж
    0.06
     dps
    0.06
    POR
    0.06
    ениях
    0.06
     Glas
    0.06
     electr
    0.06
    _PHASE
    0.06
    Act Density 0.117%

    No Known Activations