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

    Neuronpedia

    INDEX
    Explanations

    distinguishing non-english characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     négl
    0.48
     داله
    0.48
    คองโก
    0.48
    GoObject
    0.46
     ODE
    0.45
     ቤት
    0.44
     computador
    0.44
     prologue
    0.44
     程
    0.43
     achet
    0.42
    POSITIVE LOGITS
    З
    0.48
    张
    0.48
    ve
    0.47
    С
    0.46
    А
    0.45
    ो
    0.44
    е
    0.43
    위
    0.43
    uh
    0.43
    े
    0.43
    Act Density 0.000%

    No Known Activations