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

    Neuronpedia

    INDEX
    Explanations

    input prompts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Syndrome
    0.54
    ridged
    0.47
    Insights
    0.46
     Machinery
    0.46
    Hardware
    0.46
    劾
    0.46
    iseries
    0.45
    Enhanced
    0.43
    Protection
    0.43
    PhysRev
    0.43
    POSITIVE LOGITS
     input
    0.99
    输入
    0.92
    入力
    0.88
    input
    0.86
     입력
    0.83
    请输入
    0.82
     输入
    0.82
     inputted
    0.82
     Input
    0.81
     inputs
    0.79
    Act Density 0.049%

    No Known Activations