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

    Neuronpedia

    INDEX
    Explanations

    thirst and dehydration symptoms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    of
    0.88
     of
    0.80
    0.66
    리
    0.62
    a
    0.58
     врача
    0.57
     육
    0.57
     풀
    0.56
    Hern
    0.55
    Ј
    0.54
    POSITIVE LOGITS
    ती
    0.98
    नंतर
    0.84
    度和
    0.83
    ня
    0.80
    ដែល
    0.77
    കൾ
    0.75
     jedem
    0.72
    लन
    0.71
    liceerd
    0.71
    يته
    0.71
    Act Density 0.000%

    No Known Activations