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

    Neuronpedia

    INDEX
    Explanations

    relationships

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Provid
    -0.07
    -conscious
    -0.07
    authorized
    -0.07
     رز
    -0.06
    idlo
    -0.06
    aking
    -0.06
    �
    -0.06
    fusc
    -0.06
     emotionally
    -0.06
    -ass
    -0.06
    POSITIVE LOGITS
     треть
    0.07
     vữ
    0.06
     episode
    0.06
     десят
    0.06
     millones
    0.06
    ARGS
    0.06
    (tile
    0.06
     cocos
    0.06
     shout
    0.06
     úspě
    0.06
    Act Density 0.264%

    No Known Activations