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

    Neuronpedia

    INDEX
    Explanations

    i

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fires
    -0.07
     nécessaire
    -0.07
    544
    -0.07
    .trip
    -0.07
    274
    -0.07
     сет
    -0.07
     phosph
    -0.07
     LY
    -0.07
     resurgence
    -0.07
    ست
    -0.07
    POSITIVE LOGITS
    "]],↵
    0.07
    며
    0.06
    lude
    0.06
     मई
    0.06
    ково
    0.06
    ��
    0.06
    =back
    0.06
     acab
    0.06
    ardy
    0.06
     herbal
    0.06
    Act Density 0.026%

    No Known Activations