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

    Neuronpedia

    INDEX
    Explanations

    phrases beginning with okay

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    τηση
    0.41
     canv
    0.37
    احث
    0.37
     तिमाही
    0.34
     जितनी
    0.33
    )!=
    0.33
    uiswing
    0.33
     fatig
    0.32
    ucho
    0.32
    仼
    0.32
    POSITIVE LOGITS
     okay
    3.86
     ok
    3.75
     OK
    3.53
     Okay
    3.44
     Ok
    3.39
    Okay
    3.28
    Ok
    3.23
    OK
    3.20
    okay
    3.19
     alright
    3.09
    Act Density 0.316%

    No Known Activations