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

    Neuronpedia

    INDEX
    Explanations

    Foreign language/abbreviations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ormal
    -0.08
    팎
    -0.08
    stasy
    -0.07
    枯燥
    -0.07
     Hell
    -0.07
     misery
    -0.07
     Bass
    -0.07
     del
    -0.07
    gae
    -0.06
    똥
    -0.06
    POSITIVE LOGITS
    GLenum
    0.08
    מלחמת
    0.07
    ߠ
    0.07
    	ST
    0.07
     Cf
    0.07
    карт
    0.07
     filmes
    0.07
    RETURN
    0.07
     заяв
    0.07
     OID
    0.07
    Act Density 0.141%

    No Known Activations