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

    Neuronpedia

    INDEX
    Explanations

    mind

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     نو
    -0.07
    dynamic
    -0.06
     охорони
    -0.06
    lda
    -0.06
    chází
    -0.06
    istry
    -0.06
    ipherals
    -0.06
    (OS
    -0.06
     dây
    -0.06
     Tribe
    -0.06
    POSITIVE LOGITS
     Amazing
    0.07
    ↵↵↵↵↵↵↵↵↵↵
    0.06
    .org
    0.06
    SSID
    0.06
     reloadData
    0.06
     perso
    0.06
    Forbidden
    0.06
    ेद
    0.06
    ป
    0.06
    Group
    0.06
    Act Density 0.011%

    No Known Activations