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

    Neuronpedia

    INDEX
    Explanations

    sensory and material descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    loadNpm
    0.49
    ienen
    0.47
    istry
    0.46
    AllResult
    0.45
     மத
    0.45
    ij
    0.44
    onzo
    0.44
     كامل
    0.43
    क्षिप्त
    0.43
    marks
    0.42
    POSITIVE LOGITS
     underestimated
    0.49
     autoimmune
    0.45
    덬
    0.43
     mohli
    0.43
     underestimates
    0.43
     armchair
    0.42
     overestimated
    0.41
     waiting
    0.41
     tariff
    0.40
     degeneration
    0.40
    Act Density 0.006%

    No Known Activations