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

    Neuronpedia

    INDEX
    Explanations

    emphasis and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    EN
    0.30
    .
    0.30
     a
    0.30
     the
    0.29
     Einzel
    0.29
    )
    0.29
    Display
    0.29
     an
    0.28
    م
    0.28
    м
    0.27
    POSITIVE LOGITS
    雰囲気
    0.27
    ığımız
    0.26
    direccion
    0.26
     stessi
    0.26
    环境下
    0.25
    of
    0.25
     तत्वों
    0.25
    vykor
    0.25
     and
    0.25
    such
    0.25
    Act Density 0.191%

    No Known Activations