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

    Neuronpedia

    INDEX
    Explanations

    visualize the results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Est
    0.41
    getUser
    0.39
    Vote
    0.38
    铑
    0.38
     الشباب
    0.37
    erdem
    0.37
    thern
    0.37
    auce
    0.37
     vint
    0.37
     ಅಭಿ
    0.37
    POSITIVE LOGITS
    ⁦
    0.40
     medica
    0.38
    避け
    0.37
     Immutable
    0.36
    काम
    0.35
     વધી
    0.34
     Whitehall
    0.34
    치가
    0.34
     कांस
    0.34
    不受
    0.34
    Act Density 0.001%

    No Known Activations