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

    Neuronpedia

    INDEX
    Explanations

    code blocks and conditional logic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    on
    0.76
    ה
    0.76
    ੀ
    0.75
    os
    0.73
    in
    0.71
    तः
    0.68
    ième
    0.68
    اً
    0.67
    ان
    0.65
    l
    0.64
    POSITIVE LOGITS
    时候
    0.78
    াজ
    0.77
    !\!\
    0.76
     elites
    0.75
     grate
    0.75
     aversion
    0.72
    ទ្រ
    0.72
    思想
    0.70
     phosphor
    0.70
     confines
    0.70
    Act Density 0.006%

    No Known Activations