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

    Neuronpedia

    INDEX
    Explanations

    awkward

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     saliva
    -0.06
    ınıza
    -0.06
    dete
    -0.06
     mét
    -0.06
    истем
    -0.06
     comando
    -0.06
    ArgsConstructor
    -0.06
    ítulo
    -0.06
     permite
    -0.06
    _B
    -0.06
    POSITIVE LOGITS
     awkward
    0.20
     werk
    0.07
     gracefully
    0.07
    uxtap
    0.07
    offers
    0.07
     Advertising
    0.07
    �
    0.06
    _hooks
    0.06
    佳
    0.06
     hangs
    0.06
    Act Density 0.002%

    No Known Activations