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

    Neuronpedia

    INDEX
    Explanations

    forgiveness, planners, 'laadla'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    楡
    0.43
    uncertain
    0.42
    鬱
    0.40
    憩
    0.40
    ゐ
    0.40
    ები
    0.40
     ಮಹ
    0.40
    depart
    0.40
    階段
    0.40
    beams
    0.40
    POSITIVE LOGITS
    CHE
    0.52
     enige
    0.44
     asistente
    0.44
     azúcar
    0.44
    APE
    0.43
    ैश
    0.43
    apet
    0.43
    -"+
    0.43
    LException
    0.42
    anées
    0.42
    Act Density 0.065%

    No Known Activations