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

    Neuronpedia

    INDEX
    Explanations

    code snippets and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Sp
    0.34
    La
    0.27
    Al
    0.27
     Pec
    0.26
    Wood
    0.26
    Anno
    0.26
    Be
    0.25
    Br
    0.25
     creatively
    0.25
    ब्बा
    0.25
    POSITIVE LOGITS
    XSSFSheet
    0.26
    $&$-
    0.26
     থাকত
    0.26
     ڪر
    0.25
     tasmim
    0.25
     Ꭰ
    0.25
     जाते
    0.25
    ాలని
    0.24
    TextBoxColumn
    0.24
    ákat
    0.24
    Act Density 0.360%

    No Known Activations