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

    Neuronpedia

    INDEX
    Explanations

    code snippets/mixed text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kov
    -0.07
    เคล
    -0.06
     trusting
    -0.06
     ell
    -0.06
    time
    -0.06
    lates
    -0.06
     few
    -0.05
     wards
    -0.05
    .parametrize
    -0.05
    needed
    -0.05
    POSITIVE LOGITS
    }`;↵↵
    0.07
    .WHITE
    0.06
    De
    0.06
    //------------------------------------------------------------------------------↵
    0.06
     showToast
    0.06
    _playing
    0.06
    arken
    0.06
     sends
    0.06
    .Bar
    0.06
    场
    0.06
    Act Density 0.000%

    No Known Activations