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

    Neuronpedia

    INDEX
    Explanations

    ways of doing things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     flown
    0.61
     safety
    0.60
     be
    0.56
     ס
    0.55
     see
    0.55
     sobering
    0.55
     shock
    0.54
     wasteland
    0.54
     wine
    0.53
     mountain
    0.53
    POSITIVE LOGITS
     طریقے
    0.73
     प्रकारे
    0.67
     Continuando
    0.64
    方式
    0.64
     방법을
    0.63
     முறையில்
    0.62
     спосо
    0.61
     तरीके
    0.60
     способы
    0.59
     तरीकों
    0.58
    Act Density 0.698%

    No Known Activations