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

    Neuronpedia

    INDEX
    Explanations

    code/technical text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ind
    -0.07
     faker
    -0.07
     wing
    -0.07
    range
    -0.07
     courts
    -0.07
    yme
    -0.07
    anj
    -0.07
    -key
    -0.06
     wr
    -0.06
     hesitation
    -0.06
    POSITIVE LOGITS
     是否
    0.07
     مطال
    0.07
    ::::|
    0.06
    dotenv
    0.06
     تاث
    0.06
    �
    0.06
     податков
    0.06
    APolynomial
    0.06
     будут
    0.06
    basename
    0.06
    Act Density 0.000%

    No Known Activations