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

    Neuronpedia

    INDEX
    Explanations

    balancing acts and images

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Fonts
    0.46
    Alice
    0.44
    魅力
    0.43
    酵
    0.43
    Font
    0.41
     wygląd
    0.41
    樣
    0.40
    перы
    0.39
    写真
    0.39
    стью
    0.39
    POSITIVE LOGITS
     bedrooms
    0.39
     Palazzo
    0.39
     boxe
    0.38
     Haush
    0.38
     Boxing
    0.37
     Mathf
    0.37
     kotak
    0.37
     Dolom
    0.37
     ان
    0.36
     concatenate
    0.36
    Act Density 0.000%

    No Known Activations