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

    Neuronpedia

    INDEX
    Explanations

    select, selection, selected

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    udh
    0.40
    नेल
    0.38
    POSIT
    0.37
     killer
    0.35
     пози
    0.35
     Grat
    0.35
    ريب
    0.34
     cluttered
    0.34
    Killer
    0.34
    elin
    0.34
    POSITIVE LOGITS
     selection
    1.60
     Selection
    1.54
    Selection
    1.48
    selection
    1.45
     selections
    1.38
     seleção
    1.32
     सिलेक्शन
    1.30
     selecting
    1.30
     selezione
    1.30
     selección
    1.25
    Act Density 0.113%

    No Known Activations