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

    Neuronpedia

    INDEX
    Explanations

    so such

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oauth
    -0.07
     Rap
    -0.06
    eyen
    -0.06
    ай
    -0.06
    .shared
    -0.06
    )("
    -0.06
    уда
    -0.06
    ум
    -0.06
     еж
    -0.06
    ��
    -0.06
    POSITIVE LOGITS
     tend
    0.07
    되는
    0.06
     Radar
    0.06
     StyleSheet
    0.06
     advertiser
    0.06
     Confirm
    0.06
    editing
    0.06
    /)↵
    0.06
    acemark
    0.06
    ]").
    0.06
    Act Density 0.017%

    No Known Activations