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

    Neuronpedia

    INDEX
    Explanations

    maybe, realized, followed by pause

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    !
    0.66
     berbagai
    0.58
    !)
    0.54
     çeşitli
    0.54
     !
    0.53
     allerlei
    0.53
    !]
    0.52
    !"
    0.51
     interessant
    0.51
    ！
    0.51
    POSITIVE LOGITS
    𒊏
    0.46
    हों
    0.46
    RELAND
    0.45
    öll
    0.44
    Đi
    0.44
    最后的
    0.44
    IDENTITY
    0.43
    এবং
    0.43
    토
    0.43
    unità
    0.42
    Act Density 0.140%

    No Known Activations