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

    Neuronpedia

    INDEX
    Explanations

    different kind of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ist
    0.47
    process
    0.43
    upgrade
    0.42
    uncertain
    0.42
    yg
    0.41
    da
    0.40
    state
    0.40
    arnell
    0.40
    inas
    0.40
    iled
    0.39
    POSITIVE LOGITS
     than
    0.63
     niż
    0.63
     paradigms
    0.57
     altogether
    0.55
    Than
    0.53
     전혀
    0.53
    種類の
    0.50
     ніж
    0.50
     manière
    0.49
     berbeda
    0.49
    Act Density 0.103%

    No Known Activations