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

    Neuronpedia

    INDEX
    Explanations

    star

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     qualitative
    -0.06
     revolves
    -0.06
     بدون
    -0.06
    (IEnumerable
    -0.06
    _DBG
    -0.06
    ;',
    -0.06
     */;↵
    -0.06
     genuine
    -0.06
    Iss
    -0.06
    _below
    -0.06
    POSITIVE LOGITS
     star
    0.30
     Star
    0.27
    star
    0.25
    Star
    0.22
    STAR
    0.17
     STAR
    0.17
    -Star
    0.17
    -star
    0.16
    estar
    0.12
    _star
    0.11
    Act Density 0.010%

    No Known Activations