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

    Neuronpedia

    INDEX
    Explanations

    providing information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fö
    -0.07
    ْل
    -0.07
     ἀ
    -0.07
     asses
    -0.06
    ubits
    -0.06
     Pokémon
    -0.06
     Dungeon
    -0.06
     wins
    -0.06
    sets
    -0.06
     lives
    -0.06
    POSITIVE LOGITS
    대표
    0.07
    .office
    0.06
    "'↵
    0.06
     امور
    0.06
    pan
    0.06
    essenger
    0.06
     kork
    0.06
    ')↵↵↵↵
    0.06
    .cat
    0.06
    _car
    0.06
    Act Density 0.067%

    No Known Activations