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

    Neuronpedia

    INDEX
    Explanations

    purposes only

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    d
    0.44
    a
    0.42
    ூரில்
    0.41
    h
    0.38
     иннова
    0.37
     quell
    0.37
     cun
    0.36
     refer
    0.36
     supervis
    0.35
     Muay
    0.35
    POSITIVE LOGITS
     respectively
    0.47
    خته
    0.42
     તેમજ
    0.41
    ائلة
    0.41
    respectively
    0.40
    Deterministic
    0.38
     እንዲሁም
    0.38
    锭
    0.38
     sekä
    0.37
    স্যা
    0.37
    Act Density 0.042%

    No Known Activations