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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     patrol
    -0.06
     Smith
    -0.06
     passwords
    -0.06
    {},
    -0.06
     excludes
    -0.06
     Himself
    -0.06
    ocratic
    -0.06
     Mast
    -0.06
    .Comm
    -0.06
     “[
    -0.06
    POSITIVE LOGITS
     hry
    0.07
     uży
    0.07
     TreeSet
    0.06
     ASA
    0.06
    encoded
    0.06
    .getMonth
    0.06
    .currentTarget
    0.06
    .month
    0.06
    ledon
    0.06
    .NewGuid
    0.06
    Act Density 0.002%

    No Known Activations