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

    Neuronpedia

    INDEX
    Explanations

    static

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _an
    -0.07
     komm
    -0.06
     فناوری
    -0.06
    .Immutable
    -0.06
    incer
    -0.06
     objected
    -0.06
     Ala
    -0.06
     substr
    -0.06
     Quart
    -0.06
     entert
    -0.06
    POSITIVE LOGITS
     prefix
    0.07
    store
    0.06
     Ly
    0.06
    ieu
    0.06
    動
    0.06
     silky
    0.06
    	HRESULT
    0.06
    Encrypt
    0.06
     기준
    0.06
    动
    0.06
    Act Density 0.001%

    No Known Activations