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

    Neuronpedia

    INDEX
    Explanations

    iteration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -q
    -0.08
    wann
    -0.07
     최고
    -0.07
    ரும்
    -0.07
    mir
    -0.07
     know
    -0.07
     mirrors
    -0.07
     wets
    -0.07
    ப்படும்
    -0.07
    ulates
    -0.07
    POSITIVE LOGITS
     woord
    0.09
     uppercase
    0.09
     naz
    0.09
     creando
    0.08
     Tolkien
    0.08
     lettering
    0.08
     lowercase
    0.08
    氏
    0.08
     શબ્દ
    0.08
    Surname
    0.08
    Act Density 0.001%

    No Known Activations