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

    Neuronpedia

    INDEX
    Explanations

    It's

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     indi
    -0.09
     venen
    -0.08
     certify
    -0.08
    esion
    -0.08
     Goldman
    -0.07
     लेकर
    -0.07
     લઈને
    -0.07
     repudi
    -0.07
    け
    -0.07
     samot
    -0.07
    POSITIVE LOGITS
     bastante
    0.08
     fairly
    0.08
     tricky
    0.08
    复杂
    0.08
     messy
    0.08
     довольно
    0.08
     conscientious
    0.08
    _complex
    0.07
    Seems
    0.07
     rutina
    0.07
    Act Density 0.061%

    No Known Activations