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

    Neuronpedia

    INDEX
    Explanations

    as specific as possible

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ’।
    0.42
     destinés
    0.41
     більш
    0.40
     halv
    0.39
    œurs
    0.38
     ಹೆಚ್ಚಿನ
    0.38
     meeste
    0.38
    ॉप्टर
    0.38
     tâches
    0.37
    更容易
    0.37
    POSITIVE LOGITS
     as
    0.65
     както
    0.49
     όσο
    0.48
    as
    0.43
     যতটা
    0.41
     као
    0.37
     kuin
    0.36
    ដូច
    0.36
    ा
    0.36
    möglich
    0.35
    Act Density 0.050%

    No Known Activations