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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     RS
    -0.07
    INAL
    -0.07
    CS
    -0.07
     wisely
    -0.06
    SON
    -0.06
     singer
    -0.06
    PS
    -0.06
    LEN
    -0.06
    是
    -0.06
    NY
    -0.06
    POSITIVE LOGITS
     Ive
    0.07
    _hidden
    0.07
    	initial
    0.06
     Lifetime
    0.06
     Vide
    0.06
    .Sample
    0.06
    уття
    0.06
     yapan
    0.06
     ηλεκ
    0.06
     Scient
    0.06
    Act Density 0.049%

    No Known Activations