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

    Neuronpedia

    INDEX
    Explanations

    disclaimers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     annoy
    -0.07
     respectfully
    -0.07
    таки
    -0.06
    い
    -0.06
     advis
    -0.06
    ूछ
    -0.06
     Lecture
    -0.06
     outset
    -0.06
     Mention
    -0.06
    věl
    -0.06
    POSITIVE LOGITS
     maxlength
    0.06
    yne
    0.06
    .reporting
    0.06
    emean
    0.06
    ogene
    0.06
    (..
    0.06
     useSelector
    0.06
     MC
    0.06
    isex
    0.06
     HEX
    0.06
    Act Density 0.139%

    No Known Activations