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

    Neuronpedia

    INDEX
    Explanations

    Code snippets and explanations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ्ट्र
    -0.09
     ră
    -0.08
    打造
    -0.08
     naziv
    -0.08
     electricians
    -0.08
    ्ट्रेल
    -0.08
     nautical
    -0.08
    ינות
    -0.08
     kines
    -0.08
    ტრ
    -0.08
    POSITIVE LOGITS
     Bash
    0.08
     함수
    0.08
     useful
    0.08
    (x
    0.07
    .c
    0.07
    ase
    0.07
    (*
    0.07
     measurement
    0.07
    (origin
    0.07
    AL
    0.07
    Act Density 0.013%

    No Known Activations