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

    Neuronpedia

    INDEX
    Explanations

    description

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     McCull
    0.70
    strength
    0.69
     rapid
    0.68
     mags
    0.67
     decl
    0.65
    คร
    0.63
     strength
    0.62
     mag
    0.62
    fiche
    0.62
    mag
    0.60
    POSITIVE LOGITS
     describe
    0.78
     describing
    0.75
     Beschreibung
    0.74
     सीक्व
    0.73
    鼍
    0.72
    %;
    0.71
    descripcion
    0.69
    ลด
    0.69
    มาชิก
    0.68
     descrição
    0.68
    Act Density 0.006%

    No Known Activations