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

    Neuronpedia

    INDEX
    Explanations

    listing directions or places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ordinance
    0.78
    まぁ
    0.78
    );
    0.77
    Бы
    0.77
    ገባ
    0.76
    +)
    0.73
    ൺലൈ
    0.73
     Verizon
    0.72
     Trời
    0.72
     Octopus
    0.72
    POSITIVE LOGITS
    it
    1.18
    го
    0.96
     faktisk
    0.93
    те
    0.88
    ش
    0.85
    न
    0.82
    ტ
    0.82
    and
    0.80
     мебели
    0.80
     სპეცი
    0.80
    Act Density 0.000%

    No Known Activations