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

    Neuronpedia

    INDEX
    Explanations

    percentage numbers and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ט
    0.50
    ור
    0.49
    N
    0.49
    ى
    0.46
    ró
    0.44
    ూ
    0.44
    enaar
    0.43
     Temmuz
    0.43
    า
    0.42
    }$=
    0.42
    POSITIVE LOGITS
    is
    0.56
     contra
    0.54
     _
    0.50
     __
    0.49
     fission
    0.49
     ions
    0.48
     in
    0.46
     impi
    0.46
     adversarial
    0.46
     valuables
    0.45
    Act Density 0.204%

    No Known Activations