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

    Neuronpedia

    INDEX
    Explanations

    words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     причины
    -0.07
    šní
    -0.07
    .stroke
    -0.06
    AS
    -0.06
     income
    -0.06
    sında
    -0.06
     upp
    -0.06
    .sb
    -0.06
    /welcome
    -0.06
    _UNDEFINED
    -0.06
    POSITIVE LOGITS
    olist
    0.07
    _pkg
    0.07
    -ins
    0.06
    outs
    0.06
     (((
    0.06
    outed
    0.06
    outing
    0.06
     Đại
    0.06
     terminating
    0.06
    ))?
    0.06
    Act Density 0.001%

    No Known Activations