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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    バ
    -0.07
    rhs
    -0.07
    Tree
    -0.07
     >&
    -0.07
     hunts
    -0.06
    .len
    -0.06
    _D
    -0.06
     windows
    -0.06
    >C
    -0.06
    Experts
    -0.06
    POSITIVE LOGITS
     पह
    0.07
     dorsal
    0.06
    Filed
    0.06
    	define
    0.06
    서는
    0.06
     đo
    0.06
     شرق
    0.06
    -readable
    0.06
     파일
    0.06
    冷
    0.06
    Act Density 0.008%

    No Known Activations