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

    Neuronpedia

    INDEX
    Explanations

    parent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UL
    -0.07
     Radical
    -0.07
     courageous
    -0.06
    框
    -0.06
     HTML
    -0.06
    Junior
    -0.06
    ‌کند
    -0.06
    "A
    -0.06
    niejs
    -0.06
     Ου
    -0.06
    POSITIVE LOGITS
    mpr
    0.07
     tomu
    0.07
    ell
    0.07
     ipsum
    0.07
    NE
    0.06
    ostat
    0.06
    responseData
    0.06
     punto
    0.06
    .cat
    0.06
    τέρα
    0.06
    Act Density 0.005%

    No Known Activations