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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .parts
    -0.07
     взя
    -0.06
     hull
    -0.06
     deflect
    -0.06
    เสร
    -0.06
    $j
    -0.06
     edges
    -0.06
    19
    -0.06
    .Al
    -0.06
    錄
    -0.06
    POSITIVE LOGITS
    committee
    0.07
     inaug
    0.06
    !'
    0.06
     AX
    0.06
     perceived
    0.06
    .AUTH
    0.06
    !
    0.06
    !
    0.06
     Değer
    0.06
     musician
    0.06
    Act Density 0.007%

    No Known Activations