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

    Neuronpedia

    INDEX
    Explanations

    Fortran formatting characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    字母
    0.40
     tensor
    0.38
     huk
    0.38
     CMD
    0.36
    iezan
    0.36
     lettres
    0.36
     marin
    0.35
    überkü
    0.35
     Hels
    0.35
    LaunchAction
    0.35
    POSITIVE LOGITS
     Number
    0.43
    Ａ
    0.42
     Incorporation
    0.40
     א
    0.40
    Pro
    0.39
    جھ
    0.39
    Officer
    0.38
    mtext
    0.38
    𝐀
    0.38
     Officer
    0.37
    Act Density 0.000%

    No Known Activations