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

    Neuronpedia

    INDEX
    Explanations

    offering further explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    लब्
    0.59
    ם
    0.54
    0.53
    ﺎ
    0.51
    ს
    0.48
    ер
    0.48
    ers
    0.48
    𝐩
    0.48
    🆈
    0.46
    ioners
    0.46
    POSITIVE LOGITS
    л
    0.72
    a
    0.67
    া
    0.56
    aş
    0.54
    فة
    0.51
    га
    0.50
     businessman
    0.50
    ாஹ
    0.49
    க்கி
    0.49
    ા
    0.48
    Act Density 0.136%

    No Known Activations