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

    Neuronpedia

    INDEX
    Explanations

    section markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    假日
    0.47
     dianggap
    0.45
    트
    0.45
    는
    0.44
    仙
    0.44
     être
    0.44
    农
    0.43
    芰
    0.43
     affiche
    0.43
    ב
    0.43
    POSITIVE LOGITS
     poached
    0.54
     grassroots
    0.53
     subgroups
    0.52
     reais
    0.50
     ∫
    0.49
    charset
    0.48
     poppies
    0.48
     daughter
    0.48
     UNDP
    0.48
     momenta
    0.47
    Act Density 0.001%

    No Known Activations