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

    Neuronpedia

    INDEX
    Explanations

    django code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fantástico
    1.06
     puțin
    1.02
     Therapy
    1.02
     Celebration
    0.96
     Discounts
    0.96
     będzie
    0.95
     Descripción
    0.95
     Overview
    0.95
     Aspects
    0.93
     Urgent
    0.92
    POSITIVE LOGITS
    when
    0.91
    aside
    0.84
    ochlorite
    0.84
    ذه
    0.83
    u
    0.82
    Claude
    0.82
    uere
    0.78
    pharm
    0.76
    asserie
    0.76
    cite
    0.75
    Act Density 0.000%

    No Known Activations