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

    Neuronpedia

    INDEX
    Explanations

    Code/technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gió
    -0.08
     Spect
    -0.07
    νομ
    -0.07
     geg
    -0.07
    -guard
    -0.06
     Marl
    -0.06
    >Returns
    -0.06
     Olympia
    -0.06
     Improvement
    -0.06
     understands
    -0.06
    POSITIVE LOGITS
    (rules
    0.07
    0.07
    izin
    0.06
    [e
    0.06
    [
    0.06
     stringBy
    0.06
    анной
    0.06
    (_,
    0.06
    /com
    0.06
     半
    0.06
    Act Density 0.000%

    No Known Activations