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

    Neuronpedia

    INDEX
    Explanations

    math or code errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Κο
    -0.07
     conce
    -0.06
    SW
    -0.06
     deadliest
    -0.06
     þ
    -0.06
     alo
    -0.06
     seen
    -0.06
     são
    -0.06
    .generic
    -0.06
    toBe
    -0.06
    POSITIVE LOGITS
     archive
    0.06
    uggling
    0.06
    perform
    0.06
    Danny
    0.06
    Bright
    0.06
    ализации
    0.06
     раньше
    0.06
    NSMutableDictionary
    0.06
     DUI
    0.06
    ें।↵
    0.06
    Act Density 0.000%

    No Known Activations