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

    Neuronpedia

    INDEX
    Explanations

    doing or being

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     زمان
    0.43
    സിയ
    0.43
     pennies
    0.42
     Hrs
    0.42
     HRS
    0.41
     جنيه
    0.41
     دقائق
    0.41
     inducement
    0.40
     टाइम
    0.40
     অবগত
    0.39
    POSITIVE LOGITS
     /
    0.54
    arm
    0.42
    K
    0.39
    비
    0.39
    Lateral
    0.38
    Option
    0.38
    API
    0.37
    bi
    0.37
    Bench
    0.37
     ho
    0.36
    Act Density 0.000%

    No Known Activations