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

    Neuronpedia

    INDEX
    Explanations

    fox types and indices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ρωση
    0.51
    kati
    0.46
    ন
    0.46
     multin
    0.44
    खाना
    0.42
    ництво
    0.42
    Arrow
    0.42
     нала
    0.42
    ུང་
    0.40
    τηση
    0.40
    POSITIVE LOGITS
     detal
    0.57
     meinem
    0.51
     தவிர
    0.49
     ذه
    0.48
     التي
    0.47
     ذا
    0.46
    ামুটি
    0.46
     الذي
    0.46
    PanelVisual
    0.46
     হলেই
    0.46
    Act Density 0.000%

    No Known Activations