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

    Neuronpedia

    INDEX
    Explanations

    HTML code snippets

    oai_token-act-pair · gemini-2.0-flash

    HTML form attributes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    &
    -0.56
     prime
    -0.54
     Prime
    -0.53
     plus
    -0.48
     first
    -0.48
    +
    -0.47
    edi
    -0.47
     loved
    -0.46
    Di
    -0.46
     one
    -0.46
    POSITIVE LOGITS
    findpost
    1.04
     صوتيه
    0.96
    ArgsConstructor
    0.94
    SequentialGroup
    0.92
    tvguidetime
    0.92
     متعلقه
    0.85
    TagMode
    0.85
    rungsseite
    0.79
    migrationBuilder
    0.79
     للمعارف
    0.77
    Act Density 1.561%

    No Known Activations