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

    Neuronpedia

    INDEX
    Explanations

    Experience

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     crab
    -0.07
     Crab
    -0.07
     sounds
    -0.07
    ельзя
    -0.07
    ють
    -0.06
     가입
    -0.06
    riting
    -0.06
    _users
    -0.06
     vlád
    -0.06
     управления
    -0.06
    POSITIVE LOGITS
     pcm
    0.08
     Qur
    0.07
    (dm
    0.07
    銷
    0.06
    (deck
    0.06
     Interfaces
    0.06
     эффек
    0.06
     KeyError
    0.06
    @endif
    0.06
     interrupt
    0.06
    Act Density 0.007%

    No Known Activations