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

    Neuronpedia

    INDEX
    Explanations

    code blocks and inline syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    istosoma
    0.46
    inicio
    0.41
    ificador
    0.40
    ivi
    0.40
     laryng
    0.39
     únicamente
    0.39
    rió
    0.38
     empecé
    0.38
     lia
    0.38
    moja
    0.38
    POSITIVE LOGITS
    Kotlin
    0.43
     Verbrauch
    0.42
    Bruno
    0.41
    Chicken
    0.40
    Ա
    0.40
    ต้องการ
    0.40
     Pawar
    0.40
    寤
    0.39
    Adapted
    0.39
    اداس
    0.39
    Act Density 0.000%

    No Known Activations