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

    Neuronpedia

    INDEX
    Explanations

    Words indicating speech/communication

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     TIM
    -0.07
    oř
    -0.07
    .xr
    -0.06
     tqdm
    -0.06
     cor
    -0.06
    ahir
    -0.06
     orbital
    -0.06
    criptor
    -0.06
     林
    -0.06
     центр
    -0.06
    POSITIVE LOGITS
    Display
    0.07
    �
    0.07
     currentState
    0.07
     используют
    0.07
    Michelle
    0.06
     může
    0.06
     Undefined
    0.06
    Search
    0.06
     Help
    0.06
    617
    0.06
    Act Density 0.005%

    No Known Activations