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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    datetime
    -0.07
     parked
    -0.07
     Foto
    -0.06
    224
    -0.06
    \Column
    -0.06
    ์ค
    -0.06
     IData
    -0.06
    ियल
    -0.06
    423
    -0.06
    WithError
    -0.06
    POSITIVE LOGITS
     kys
    0.06
     CancellationToken
    0.06
     infertility
    0.06
     günü
    0.06
     disagreements
    0.06
     Pols
    0.06
     pov
    0.06
    endas
    0.06
     život
    0.06
     солн
    0.06
    Act Density 0.024%

    No Known Activations