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

    Neuronpedia

    INDEX
    Explanations

    color codes and celebration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ри
    0.52
    level
    0.51
    thiophene
    0.50
    setLevel
    0.49
    rate
    0.48
    钚
    0.46
    Tile
    0.46
     MNRAS
    0.46
     FAQ
    0.46
    бут
    0.46
    POSITIVE LOGITS
     temer
    0.57
     toma
    0.54
     sacks
    0.54
     sadde
    0.53
     sette
    0.53
    UTTON
    0.52
     organes
    0.51
    apal
    0.51
     Jackets
    0.51
     otto
    0.51
    Act Density 0.000%

    No Known Activations