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

    Neuronpedia

    INDEX
    Explanations

    data analysis and ease of use

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ath
    0.45
     nuestras
    0.43
     přímo
    0.43
    ৤
    0.43
    áty
    0.42
    atoare
    0.42
    equ
    0.42
    َّا
    0.42
    ρίες
    0.42
    aqu
    0.41
    POSITIVE LOGITS
     Touchable
    0.49
     choker
    0.49
     Einsatz
    0.47
     ChIP
    0.47
     삽
    0.46
     الحل
    0.45
    ขึ้น
    0.45
     Disk
    0.44
     메시
    0.44
    最具
    0.44
    Act Density 0.000%

    No Known Activations