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

    Neuronpedia

    INDEX
    Explanations

    War

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     supplemented
    -0.07
     clicked
    -0.07
     bilinen
    -0.07
    こそ
    -0.07
     Ax
    -0.06
    다면
    -0.06
    Probably
    -0.06
     SCALE
    -0.06
     hurt
    -0.06
    بالإنجليزية
    -0.06
    POSITIVE LOGITS
     trưng
    0.06
    قف
    0.06
     صنعت
    0.06
     dispenser
    0.06
    cosystem
    0.06
     constructing
    0.06
    hud
    0.06
    赏
    0.06
    gets
    0.06
    浮
    0.05
    Act Density 0.079%

    No Known Activations