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

    Neuronpedia

    INDEX
    Explanations

    Code/technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -destruct
    -0.07
    敢
    -0.06
    又
    -0.06
     richest
    -0.06
    )의
    -0.06
    okrat
    -0.06
    ��
    -0.06
     Sgt
    -0.06
    τερη
    -0.06
    }")
↵
    -0.06
    POSITIVE LOGITS
    .payload
    0.08
     CB
    0.07
     let
    0.07
    _TRUNC
    0.07
    AA
    0.06
    (paren
    0.06
     Finals
    0.06
    /gen
    0.06
    (par
    0.06
    LU
    0.06
    Act Density 0.000%

    No Known Activations