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

    Neuronpedia

    INDEX
    Explanations

    print statement following word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ský
    0.49
    ұл
    0.44
    idence
    0.43
    вость
    0.42
     podmín
    0.41
     హత్య
    0.41
     hose
    0.41
     എന്നത്
    0.41
     അത്
    0.40
    ibilidades
    0.40
    POSITIVE LOGITS
    Micro
    0.43
     diplomas
    0.43
     KIR
    0.40
     MICRO
    0.39
     Micro
    0.39
    Kor
    0.39
    BPACK
    0.38
    ТР
    0.38
    빡
    0.38
     micro
    0.38
    Act Density 10.732%

    No Known Activations