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

    Neuronpedia

    INDEX
    Explanations

    inside

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Net
    -0.08
    OUN
    -0.07
     tham
    -0.07
     Nathan
    -0.07
     Terms
    -0.07
     المنت
    -0.07
     Gareth
    -0.06
     Тому
    -0.06
     Ka
    -0.06
     萬
    -0.06
    POSITIVE LOGITS
     inside
    0.19
     Inside
    0.15
    Inside
    0.14
    inside
    0.12
     insider
    0.09
     внутри
    0.08
     dentro
    0.08
    си
    0.08
    _ING
    0.07
    insky
    0.07
    Act Density 0.015%

    No Known Activations