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

    Neuronpedia

    INDEX
    Explanations

    into the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     amputation
    0.43
     dysplasia
    0.43
     Find
    0.42
     clade
    0.42
     Parkinson
    0.41
     tassel
    0.40
     bile
    0.40
     genotype
    0.40
    larım
    0.40
    च्चय
    0.39
    POSITIVE LOGITS
     direto
    0.46
    汇
    0.46
    serviceTime
    0.45
    ósito
    0.44
    يز
    0.43
    ក៏
    0.42
    isée
    0.42
     शिप
    0.42
     Boiling
    0.42
    árez
    0.42
    Act Density 0.002%

    No Known Activations