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

    Neuronpedia

    INDEX
    Explanations

    copy and paste

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.44
    น
    0.43
    sla
    0.38
    ی
    0.38
    ม
    0.38
     aquare
    0.37
    ים
    0.37
    มัน
    0.37
    sning
    0.37
     який
    0.36
    POSITIVE LOGITS
    as
    0.56
     as
    0.43
     coalitions
    0.41
    ेंट
    0.40
     pitches
    0.40
     conductas
    0.40
    νο
    0.40
     votes
    0.40
    istes
    0.39
    సీపీ
    0.39
    Act Density 0.127%

    No Known Activations