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

    Neuronpedia

    INDEX
    Explanations

    linking to related information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     потребности
    0.55
     функ
    0.51
    apayati
    0.49
    acariy
    0.49
    mäßige
    0.48
     една
    0.48
    ้น
    0.47
     обозна
    0.47
    žas
    0.47
     использование
    0.46
    POSITIVE LOGITS
    ين
    0.57
    '
    0.54
    ק
    0.52
    ک
    0.52
     associated
    0.50
    🈚
    0.50
    配套
    0.50
    ł
    0.50
    یان
    0.49
     corresponding
    0.49
    Act Density 0.059%

    No Known Activations