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

    Neuronpedia

    INDEX
    Explanations

    Math and coding terms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .strict
    -0.07
     dungeon
    -0.07
    LESS
    -0.07
     Choosing
    -0.06
    utters
    -0.06
     documenting
    -0.06
    装修
    -0.06
    sono
    -0.06
    iture
    -0.06
    се
    -0.06
    POSITIVE LOGITS
     Waterloo
    0.07
     IAM
    0.06
    .getFirst
    0.06
    防护
    0.06
     billing
    0.06
    "One
    0.06
    ’all
    0.06
    رب
    0.06
    onyms
    0.06
    iamond
    0.06
    Act Density 0.009%

    No Known Activations