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

    Neuronpedia

    INDEX
    Explanations

    scientific and technical descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ，
    0.57
     It
    0.49
    ،
    0.47
     anf
    0.46
    ד
    0.46
    л
    0.46
     in
    0.46
    प
    0.45
    \|^{
    0.44
     loses
    0.44
    POSITIVE LOGITS
    Music
    0.51
     జాగ్ర
    0.50
     광고
    0.49
     drž
    0.48
    rocław
    0.48
     প্রতিষ্ঠ
    0.48
     সঙ্গীতের
    0.47
     Obrig
    0.47
    বাধিকার
    0.47
     ब्याज
    0.46
    Act Density 0.000%

    No Known Activations