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

    Neuronpedia

    INDEX
    Explanations

    Months

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    840
    -0.06
     Gord
    -0.06
     аллерг
    -0.06
    bcm
    -0.06
    fraction
    -0.06
     NCAA
    -0.06
    plevel
    -0.06
     goal
    -0.06
    eto
    -0.05
    _WR
    -0.05
    POSITIVE LOGITS
    }}↵↵
    0.07
     summer
    0.07
     виснов
    0.07
    RoutingModule
    0.07
    (CharSequence
    0.06
    respond
    0.06
    역
    0.06
    恒
    0.06
     下跌
    0.06
    Measured
    0.06
    Act Density 0.015%

    No Known Activations