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

    Neuronpedia

    INDEX
    Explanations

    lack or inaction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    etition
    0.38
    hse
    0.38
    V
    0.38
    enger
    0.38
    anders
    0.37
    öld
    0.37
    िज़
    0.36
    VOID
    0.36
    oure
    0.36
    Ver
    0.36
    POSITIVE LOGITS
     übrigens
    0.73
     eigenlijk
    0.67
     البته
    0.64
     sebenarnya
    0.63
     egent
    0.63
     admittedly
    0.61
     hopefully
    0.59
     siis
    0.59
     кстати
    0.58
    hopefully
    0.57
    Act Density 0.028%

    No Known Activations