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

    Neuronpedia

    INDEX
    Explanations

    tradition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     snakes
    -0.08
    Reflection
    -0.07
    盗
    -0.07
     confl
    -0.06
     Barnett
    -0.06
     dum
    -0.06
     Fiji
    -0.06
     x
    -0.06
    /share
    -0.06
    가
    -0.06
    POSITIVE LOGITS
    atürk
    0.06
    REQUIRED
    0.06
     그래
    0.06
    <?=$
    0.06
     quotas
    0.06
     pá
    0.06
     perks
    0.06
    меть
    0.06
    ограф
    0.06
    nofollow
    0.06
    Act Density 0.152%

    No Known Activations