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

    Neuronpedia

    INDEX
    Explanations

    introduction of purpose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    imu
    0.49
    rps
    0.48
    ową
    0.48
    nn
    0.47
    un
    0.47
    ms
    0.47
    ra
    0.46
    ru
    0.46
     רא
    0.45
     directions
    0.45
    POSITIVE LOGITS
    Sexy
    0.47
     primed
    0.45
     alleviate
    0.44
    Bor
    0.44
    Celebrate
    0.44
    Patients
    0.43
     axisymmetric
    0.43
     have
    0.43
    Estado
    0.43
    Society
    0.42
    Act Density 0.002%

    No Known Activations