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

    Neuronpedia

    INDEX
    Explanations

    section titles and outlines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    on
    0.53
    at
    0.48
    el
    0.47
     summar
    0.46
     ranking
    0.46
     conspiracy
    0.46
    asa
    0.46
    ר
    0.46
    ad
    0.45
    ap
    0.45
    POSITIVE LOGITS
     парт
    0.39
    ޙ
    0.38
     จง
    0.37
    ваем
    0.37
     הראש
    0.36
     obligaciones
    0.35
    udging
    0.35
     требуется
    0.35
     facultad
    0.34
     সর্বদা
    0.34
    Act Density 0.000%

    No Known Activations