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

    Neuronpedia

    INDEX
    Explanations

    equations and formulas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ec
    0.50
    生态
    0.49
     Ec
    0.47
     kang
    0.43
     nisi
    0.43
    otoxicity
    0.43
    生
    0.41
     Ecological
    0.41
     Quiz
    0.40
    生態
    0.40
    POSITIVE LOGITS
    維持
    0.37
    0.36
    ="'.$
    0.35
    利
    0.35
    兩
    0.35
    Tra
    0.34
    Ny
    0.34
     دنبال
    0.34
     وكذلك
    0.34
    涎
    0.34
    Act Density 0.000%

    No Known Activations