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

    Neuronpedia

    INDEX
    Explanations

    icle

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Liberals
    -0.07
     unacceptable
    -0.07
     subtract
    -0.07
    	Create
    -0.06
    Changing
    -0.06
    за
    -0.06
     representatives
    -0.06
     utterly
    -0.06
     prohibit
    -0.06
     exchanges
    -0.06
    POSITIVE LOGITS
    εβ
    0.07
    -mf
    0.06
     أع
    0.06
     contextual
    0.06
    @Json
    0.06
     nokt
    0.06
    _HEIGHT
    0.06
    ("/")
    0.06
    .Once
    0.06
     fz
    0.05
    Act Density 0.003%

    No Known Activations