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

    Neuronpedia

    INDEX
    Explanations

    general vs specific

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (=
    0.50
    (=
    0.49
    ene
    0.47
     कष्ट
    0.47
    amal
    0.46
     (&
    0.45
    inch
    0.44
    utiliser
    0.44
    ENE
    0.44
    1
    0.44
    POSITIVE LOGITS
     incomplète
    0.42
     transporting
    0.41
     Camilla
    0.41
    жнему
    0.39
    我相信
    0.39
     addressing
    0.39
     possiamo
    0.39
     inheriting
    0.38
     wasn
    0.38
    不仅仅
    0.38
    Act Density 0.007%

    No Known Activations