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

    Neuronpedia

    INDEX
    Explanations

    two-letter uppercase sequences like FD

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     いき
    0.39
    姬
    0.36
    itario
    0.35
     crib
    0.35
    ArrayBox
    0.35
    bfc
    0.34
    仨
    0.34
    ிருக்கிறது
    0.34
    ุท
    0.33
     冖
    0.33
    POSITIVE LOGITS
     GD
    2.72
     FD
    2.66
     PD
    2.55
     VD
    2.50
     KD
    2.45
    FD
    2.44
     TD
    2.44
     BD
    2.44
     JD
    2.44
    GD
    2.42
    Act Density 0.241%

    No Known Activations