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

    Neuronpedia

    INDEX
    Explanations

    mixed languages and topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    as
    2.03
    {{{
    1.88
     सिलसिले
    1.71
    AS
    1.65
    excluding
    1.54
    {{
    1.54
    G
    1.52
     така
    1.52
     mett
    1.51
     छूट
    1.51
    POSITIVE LOGITS
    orems
    2.07
    ног
    2.04
    س
    2.02
    𒊏
    1.95
    ḕ
    1.85
    ੌ
    1.84
     nauk
    1.83
    үүл
    1.82
     endExpNow
    1.79
     gång
    1.78
    Act Density 0.000%

    No Known Activations