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

    Neuronpedia

    INDEX
    Explanations

    Il

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Device
    -0.06
    ้าห
    -0.06
    Sensor
    -0.06
    OPS
    -0.06
    ifestyle
    -0.06
    雅
    -0.06
    ======
    -0.06
    Markers
    -0.06
    _checksum
    -0.06
     schwar
    -0.06
    POSITIVE LOGITS
    -il
    0.07
    (IL
    0.07
    ุษ
    0.07
     scalp
    0.06
    iedad
    0.06
    rl
    0.06
    (dir
    0.06
    102
    0.06
     bundled
    0.06
     phil
    0.06
    Act Density 0.005%

    No Known Activations