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

    Neuronpedia

    INDEX
    Explanations

    definitions and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Calibration
    0.41
    Debug
    0.39
    Discovery
    0.38
     Discovery
    0.38
     высо
    0.37
     Limestone
    0.37
     discovery
    0.37
    Coal
    0.37
    جست
    0.37
    每次
    0.37
    POSITIVE LOGITS
     vorbere
    0.49
     zaji
    0.46
     depriving
    0.46
    lombok
    0.45
     akan
    0.45
    \,\
    0.45
    បញ្ចប់
    0.45
     denoted
    0.44
    lusconi
    0.44
    zantine
    0.44
    Act Density 0.000%

    No Known Activations