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

    Neuronpedia

    INDEX
    Explanations

    inner thoughts/feelings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _CALL
    -0.08
    -duration
    -0.08
    -util
    -0.07
    making
    -0.07
     Landsc
    -0.07
    776
    -0.07
    以来
    -0.07
     landscapes
    -0.07
     temporal
    -0.07
    _call
    -0.07
    POSITIVE LOGITS
     underneath
    0.12
     underlying
    0.10
     وراء
    0.10
     sebenarnya
    0.09
     daadwerk
    0.09
     сути
    0.09
     と
    0.09
     Somehow
    0.09
     werkelijkheid
    0.09
    实际上
    0.09
    Act Density 0.030%

    No Known Activations