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

    Neuronpedia

    INDEX
    Explanations

    here, this, information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dhammo
    0.44
     поведения
    0.42
     ettha
    0.41
    umlu
    0.40
    umim
    0.40
    anst
    0.40
     obliquely
    0.40
     intricately
    0.39
    oceras
    0.39
    anta
    0.39
    POSITIVE LOGITS
    克
    0.43
    支出
    0.40
    calibration
    0.40
    定向
    0.40
    कल्
    0.39
    我
    0.39
    calories
    0.39
    م
    0.39
    Firebase
    0.38
    б
    0.38
    Act Density 0.002%

    No Known Activations