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

    Neuronpedia

    INDEX
    Explanations

    website errors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Eine
    0.92
    Breast
    0.82
     vân
    0.81
    ﮟ
    0.81
    extras
    0.80
     Tetapi
    0.80
     来自
    0.80
    tir
    0.80
    Ideas
    0.80
     cinquième
    0.79
    POSITIVE LOGITS
    ни
    1.19
    и
    1.14
    ان
    1.07
    э
    1.02
    ิ
    0.97
    ен
    0.91
    ими
    0.90
    い
    0.89
    াল
    0.87
    י
    0.87
    Act Density 0.000%

    No Known Activations