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

    Neuronpedia

    INDEX
    Explanations

    strong affirmation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ideias
    0.48
     ideas
    0.47
     idées
    0.46
     dossiers
    0.44
    ниц
    0.43
     hints
    0.43
     estran
    0.43
    Ideas
    0.42
     mocks
    0.42
     идеи
    0.42
    POSITIVE LOGITS
    ther
    0.53
    ths
    0.49
    の場合
    0.46
     tasmim
    0.45
    јединачна
    0.45
    foresaid
    0.45
    latego
    0.44
    trk
    0.43
    treatment
    0.43
    oddsidemargin
    0.43
    Act Density 0.007%

    No Known Activations