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

    Neuronpedia

    INDEX
    Explanations

    categories, explanations, needs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ależ
    0.43
    沁
    0.42
    เงิน
    0.37
    能量
    0.37
    же
    0.37
    ைகளை
    0.37
    alá
    0.37
    रासत
    0.37
    ப்புகளை
    0.36
    कैसे
    0.36
    POSITIVE LOGITS
    രും
    0.51
     joked
    0.42
     rue
    0.40
    ruzione
    0.40
     upheld
    0.39
     remain
    0.39
     image
    0.39
     wasteland
    0.38
     breakdown
    0.38
     comment
    0.38
    Act Density 0.000%

    No Known Activations