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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ('../
    -0.07
    animation
    -0.06
     mots
    -0.06
     CALL
    -0.06
     Peer
    -0.06
    .manager
    -0.06
    ливості
    -0.06
     görül
    -0.06
     años
    -0.06
     lle
    -0.06
    POSITIVE LOGITS
    )(__
    0.07
     احمد
    0.07
    (ev
    0.07
     합니다
    0.06
     )↵↵↵↵↵↵↵↵
    0.06
     intermediary
    0.06
    arParams
    0.06
    atak
    0.06
    ὰ
    0.06
    .into
    0.06
    Act Density 0.016%

    No Known Activations