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

    Neuronpedia

    INDEX
    Explanations

    directional movement or numerical comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DanhMucSP
    0.41
    Despatx
    0.40
    castellan
    0.39
    BrNO
    0.39
    JlcG
    0.39
    GEBURTS
    0.39
     бекер
    0.39
    酈
    0.39
    🗒
    0.38
    LOTRE
    0.38
    POSITIVE LOGITS
    0.54
     and
    0.54
     M
    0.51
    1
    0.49
     L
    0.48
     +
    0.48
     C
    0.48
    5
    0.46
     N
    0.46
    6
    0.46
    Act Density 0.190%

    No Known Activations