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

    Neuronpedia

    INDEX
    Explanations

    Asking or answering questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Vac
    -0.08
    쓰
    -0.07
    ़
    -0.07
    .creation
    -0.06
    _mix
    -0.06
    zero
    -0.06
    _qu
    -0.06
    лены
    -0.06
    нять
    -0.06
    onal
    -0.06
    POSITIVE LOGITS
     그냥
    0.07
    -Allow
    0.07
    .IsChecked
    0.07
     uğra
    0.06
    .Claims
    0.06
    Because
    0.06
    _INST
    0.06
     Because
    0.06
     Marijuana
    0.06
     crashed
    0.06
    Act Density 0.007%

    No Known Activations