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

    Neuronpedia

    INDEX
    Explanations

    sentence punctuation

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    чатку
    0.68
    czaj
    0.59
    𒆳
    0.59
    торой
    0.58
     améric
    0.57
     incompl
    0.57
     Seguridad
    0.57
     integrado
    0.57
    근
    0.57
    ረሻ
    0.56
    POSITIVE LOGITS
    ."
    0.66
    ''.
    0.66
     হওয়ায়
    0.61
    .\\
    0.60
    .'
    0.59
    .''
    0.58
     thus
    0.57
    ..
    0.57
    ".
    0.56
    .)
    0.56
    Act Density 0.000%

    No Known Activations