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

    Neuronpedia

    INDEX
    Explanations

    individual and single entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    vature
    0.38
    唤
    0.36
    ureux
    0.34
    ્રે
    0.33
     संवैधानिक
    0.33
    ামে
    0.32
    ebles
    0.32
    issants
    0.32
    ium
    0.32
    valho
    0.32
    POSITIVE LOGITS
     individual
    1.78
    individual
    1.71
     individuale
    1.65
     einzel
    1.63
    Individual
    1.63
     individuales
    1.63
     individuais
    1.61
     individually
    1.58
     einzelne
    1.56
     Individual
    1.55
    Act Density 0.380%

    No Known Activations