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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    emen
    -0.31
    oge
    -0.30
    erness
    -0.29
    KEN
    -0.28
    imas
    -0.26
     Hassan
    -0.26
    ovan
    -0.25
     Kg
    -0.25
    ienes
    -0.25
     evacuated
    -0.24
    POSITIVE LOGITS
    çIJ¢ç£¨
    0.29
    çģ«æĺŁ
    0.28
     trunc
    0.26
    perimental
    0.26
    erd
    0.26
    éĩı产
    0.25
    оде
    0.25
    etch
    0.25
     Du
    0.24
    å¸Ĥ
    0.24
    Act Density 0.041%

    No Known Activations