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

    Neuronpedia

    INDEX
    Explanations

    boundary setting and violations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    اين
    1.09
    ري
    1.06
     alcoved
    0.98
    ва
    0.95
    ра
    0.94
    ба
    0.94
    в
    0.90
    j
    0.89
    CUSSION
    0.89
    ш
    0.89
    POSITIVE LOGITS
    i
    1.25
    er
    1.20
    iin
    1.13
    el
    1.11
    et
    1.11
    as
    1.05
    ir
    1.04
     for
    1.01
    ก
    1.01
    am
    0.98
    Act Density 0.022%

    No Known Activations