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

    Neuronpedia

    INDEX
    Explanations

    cannot fulfill request

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     during
    0.75
     lungo
    0.74
     EVERY
    0.73
     perceived
    0.72
     durante
    0.72
     along
    0.71
     alongside
    0.71
     eaves
    0.70
     toward
    0.70
     बिफोर
    0.70
    POSITIVE LOGITS
    ጠት
    0.79
    ^{+}
    0.76
    ס
    0.74
     সাহায্য
    0.73
    ቻል
    0.72
    某种
    0.72
    }^{-},
    0.70
    寻找
    0.70
    獲
    0.70
    更好的
    0.69
    Act Density 0.208%

    No Known Activations