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

    Neuronpedia

    INDEX
    Explanations

    punctuation in code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Rails
    -0.07
     wind
    -0.07
    นาน
    -0.06
    334
    -0.06
    angling
    -0.06
     damage
    -0.06
     Keys
    -0.06
    angled
    -0.06
    ---------↵↵
    -0.06
    altitude
    -0.06
    POSITIVE LOGITS
    :[↵
    0.08
    (begin
    0.07
    _emp
    0.07
    接着
    0.06
    ="$(
    0.06
    )').
    0.06
    ``,
    0.06
    _.
    0.06
     skvěl
    0.06
    .exec
    0.06
    Act Density 0.003%

    No Known Activations