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

    Neuronpedia

    INDEX
    Explanations

    specifications including Low or High

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pedigree
    0.82
     grotesque
    0.80
     rustic
    0.80
     Rustic
    0.78
     abstract
    0.72
     proverb
    0.71
     academic
    0.71
     dimerization
    0.70
     Fn
    0.70
     coaxial
    0.69
    POSITIVE LOGITS
    fort
    1.68
    inthe
    1.67
    ont
    1.42
    ofthe
    1.39
     withd
    1.35
    atthe
    1.34
    fors
    1.33
    notin
    1.32
    forte
    1.28
     ofthe
    1.26
    Act Density 0.197%

    No Known Activations