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

    Neuronpedia

    INDEX
    Explanations

    async tasks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     alleles
    0.90
     automobiles
    0.89
     ICH
    0.78
     domain
    0.78
     alas
    0.77
     purpos
    0.76
     genomics
    0.76
     traversal
    0.76
     midwifery
    0.75
    notin
    0.75
    POSITIVE LOGITS
    ؤ
    0.89
    AMENT
    0.85
    ڵ
    0.84
    [{
    0.81
    ه
    0.81
     Sometimes
    0.80
    ו
    0.80
    ição
    0.78
    [`
    0.77
    ridos
    0.77
    Act Density 0.003%

    No Known Activations