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

    Neuronpedia

    INDEX
    Explanations

    Explosives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    准
    -0.07
     Liberation
    -0.07
    άλ
    -0.06
     merely
    -0.06
    атки
    -0.06
     knull
    -0.06
    aes
    -0.06
     Nelson
    -0.06
     Andrews
    -0.06
     eliminated
    -0.06
    POSITIVE LOGITS
    (MigrationBuilder
    0.07
    .Maximum
    0.07
     favourites
    0.06
    Criteria
    0.06
    _RM
    0.06
    SCRI
    0.06
    ercicio
    0.06
    しても
    0.06
    llib
    0.06
     femme
    0.06
    Act Density 0.039%

    No Known Activations