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

    Neuronpedia

    INDEX
    Explanations

    multiple forms

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Hinweise
    0.53
    lename
    0.51
     месяц
    0.49
     слой
    0.48
     راستہ
    0.48
     имя
    0.46
     فیصلے
    0.46
     informace
    0.46
    Hour
    0.46
     zespół
    0.45
    POSITIVE LOGITS
     environments
    1.65
     formats
    1.58
     climates
    1.58
     regimes
    1.55
     styles
    1.55
     types
    1.53
     regions
    1.53
     sections
    1.52
     categories
    1.52
     phases
    1.49
    Act Density 4.301%

    No Known Activations