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

    Neuronpedia

    INDEX
    Explanations

    bomb

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     AS
    -0.08
    (cat
    -0.08
    PLEX
    -0.07
    exo
    -0.07
     lettuce
    -0.07
     menus
    -0.07
     complexes
    -0.06
     Clayton
    -0.06
     rut
    -0.06
     Ley
    -0.06
    POSITIVE LOGITS
     bombed
    0.12
     bomb
    0.11
     bombs
    0.11
    bomb
    0.11
     Bomb
    0.10
     bombing
    0.10
    Bomb
    0.10
     bom
    0.09
     Bom
    0.08
     bombers
    0.07
    Act Density 0.006%

    No Known Activations