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

    Neuronpedia

    INDEX
    Explanations

    instructional verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     in
    0.50
     در
    0.47
     algebras
    0.44
     уйный
    0.42
     ไหร่
    0.41
     predicts
    0.41
     pandemics
    0.41
    2
    0.41
     уйнау
    0.40
     complicates
    0.40
    POSITIVE LOGITS
    on
    0.51
    ano
    0.46
    one
    0.46
    m
    0.46
    to
    0.45
    as
    0.44
     G
    0.44
    ą
    0.43
    ul
    0.41
    ت
    0.41
    Act Density 2.302%

    No Known Activations