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

    Neuronpedia

    INDEX
    Explanations

    your majesty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     numerosas
    0.46
     numerous
    0.42
     numerosos
    0.40
    illus
    0.39
     studs
    0.39
     planes
    0.38
     minima
    0.38
     minions
    0.38
     planos
    0.38
     Enter
    0.38
    POSITIVE LOGITS
    eken
    0.41
    株式
    0.40
     Procur
    0.39
     jakości
    0.38
    brane
    0.38
     hereof
    0.38
    ެ
    0.38
    istung
    0.38
    濩
    0.38
    ซีน
    0.38
    Act Density 0.001%

    No Known Activations