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

    Neuronpedia

    INDEX
    Explanations

    punctuation and conjunctions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    鬼
    -0.06
    scoped
    -0.06
    れる
    -0.06
    ambient
    -0.06
    table
    -0.06
     chaotic
    -0.06
     openings
    -0.05
    false
    -0.05
    reading
    -0.05
    lines
    -0.05
    POSITIVE LOGITS
     incred
    0.07
    .Meta
    0.06
     Skyl
    0.06
    (db
    0.06
    �
    0.06
     Consult
    0.06
    *)↵↵
    0.06
    -trash
    0.06
     �
    0.06
    (jsonPath
    0.06
    Act Density 0.067%

    No Known Activations