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

    Neuronpedia

    INDEX
    Explanations

    SPF, screens, vision, nationalism, parks, fitting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ano
    0.51
    ambuk
    0.46
    atot
    0.45
    день
    0.44
    amboat
    0.43
    ऊंगी
    0.43
    oqu
    0.43
    atil
    0.43
    ró
    0.43
     પ્રથમ
    0.43
    POSITIVE LOGITS
    骂
    0.49
    损伤
    0.44
     approbation
    0.44
    激发
    0.43
    夸
    0.42
     \
    0.41
     Motto
    0.41
     Lemmas
    0.41
     Controversy
    0.41
     Themen
    0.40
    Act Density 0.004%

    No Known Activations