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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     DISCLAIM
    -0.08
    .getRandom
    -0.07
     Phones
    -0.06
     SHIPPING
    -0.06
     Donne
    -0.06
    	override
    -0.06
     reflects
    -0.06
    .=
    -0.06
    itemap
    -0.06
    minute
    -0.06
    POSITIVE LOGITS
     stoi
    0.07
     送
    0.07
    _comb
    0.06
    的地
    0.06
    估
    0.06
    (Symbol
    0.06
     optical
    0.06
    pop
    0.06
    ısıt
    0.06
     page
    0.06
    Act Density 0.003%

    No Known Activations