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

    Neuronpedia

    INDEX
    Explanations

    professionals make recommendations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    чу
    0.42
     convocatoria
    0.41
     Gathering
    0.38
     Toilet
    0.37
    だって
    0.37
    IZZ
    0.37
     Injury
    0.36
    стого
    0.36
     Sentencing
    0.36
    豊
    0.35
    POSITIVE LOGITS
     machines
    0.43
     وبه
    0.40
    =((
    0.39
     المك
    0.38
    䄪
    0.38
    *((
    0.37
    irect
    0.37
     മാന
    0.37
     സാധ
    0.37
    ایط
    0.37
    Act Density 0.000%

    No Known Activations