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

    Neuronpedia

    INDEX
    Explanations

    3

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    绂
    -0.07
     millennium
    -0.07
    (ViewGroup
    -0.07
    ungkin
    -0.07
    转化
    -0.06
    .Kind
    -0.06
    .inflate
    -0.06
    itim
    -0.06
    usu
    -0.06
    -switch
    -0.06
    POSITIVE LOGITS
     blackjack
    0.07
     Receive
    0.07
    �
    0.07
     heavy
    0.07
    /perl
    0.07
    プログラム
    0.07
    follow
    0.07
     safeguards
    0.07
     rek
    0.07
     אר
    0.07
    Act Density 0.004%

    No Known Activations