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

    Neuronpedia

    INDEX
    Explanations

    planting initiatives and development

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused0>
    0.41
    itte
    0.41
    धित
    0.41
     желательно
    0.40
    ssch
    0.40
     Helsing
    0.38
    १९
    0.38
    icrobial
    0.38
    mht
    0.38
    adecimal
    0.37
    POSITIVE LOGITS
     attraction
    0.43
     relation
    0.41
     suggest
    0.40
     regression
    0.40
     relations
    0.40
     Attraction
    0.39
     relações
    0.39
     atrak
    0.39
     Nase
    0.39
     கொரோ
    0.38
    Act Density 0.000%

    No Known Activations