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

    Neuronpedia

    INDEX
    Explanations

    research, specification, switching

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    0.51
    影響
    0.48
     komen
    0.48
    looped
    0.47
    譲
    0.46
    saturation
    0.46
    tMap
    0.45
    loadtxt
    0.45
     ಬರ
    0.44
    寬
    0.43
    POSITIVE LOGITS
    ators
    0.51
     Presidente
    0.49
     of
    0.49
     Ministerio
    0.49
     CHAPTER
    0.48
     regiones
    0.48
     purpos
    0.48
    ilia
    0.47
     Factories
    0.47
     Etiquetas
    0.46
    Act Density 0.000%

    No Known Activations