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

    Neuronpedia

    INDEX
    Explanations

    document.addEventListener

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ty
    0.44
     f
    0.41
     cab
    0.41
     according
    0.40
     GRID
    0.40
     all
    0.39
     CAB
    0.38
     stairs
    0.38
     All
    0.38
     str
    0.37
    POSITIVE LOGITS
    प्रभात
    0.43
     घण्ट
    0.42
     పాత్ర
    0.42
    Referring
    0.41
    weise
    0.41
    ദ്യ
    0.41
    irtschaft
    0.41
     আরম্ভ
    0.41
    InitFlag
    0.40
     आरंभ
    0.40
    Act Density 0.000%

    No Known Activations