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

    Neuronpedia

    INDEX
    Explanations

    making code easily understood

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tank
    0.45
     edge
    0.43
     fo
    0.43
    巉
    0.41
     Colombia
    0.40
     Encoding
    0.40
     Examples
    0.40
     S
    0.39
     warranty
    0.39
     Mattress
    0.39
    POSITIVE LOGITS
    jv
    0.45
    呆
    0.45
     点击
    0.43
    increased
    0.42
    恒
    0.42
    arked
    0.41
     научных
    0.41
     बढ़ाने
    0.41
    absch
    0.41
    阖
    0.41
    Act Density 0.005%

    No Known Activations