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

    Neuronpedia

    INDEX
    Explanations

    technical assignments and data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     simples
    0.47
     kleine
    0.44
     kecil
    0.40
     semplice
    0.40
     einfache
    0.40
     stille
    0.39
     semplici
    0.39
     kleinen
    0.39
     garis
    0.38
     petits
    0.38
    POSITIVE LOGITS
    以及
    0.52
    高
    0.51
    ve
    0.49
    大
    0.48
    ile
    0.47
    До
    0.47
    <0x89>
    0.46
    Γ
    0.46
    AND
    0.46
    使用
    0.45
    Act Density 0.307%

    No Known Activations