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

    Neuronpedia

    INDEX
    Explanations

    responsible

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     queues
    -0.06
    =@
    -0.06
     letras
    -0.06
    Ark
    -0.06
    calling
    -0.06
     Assert
    -0.05
    -con
    -0.05
    File
    -0.05
     Alf
    -0.05
    Dia
    -0.05
    POSITIVE LOGITS
     forge
    0.08
     cognition
    0.07
    ینگ
    0.07
     bě
    0.07
    atty
    0.07
    ern
    0.07
    زی
    0.07
    -induced
    0.07
     getPrice
    0.07
    надлеж
    0.07
    Act Density 0.002%

    No Known Activations