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

    Neuronpedia

    INDEX
    Explanations

    dust

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    大äºĭ
    -0.31
    éĩį大
    -0.28
    åĨħéĻĨ
    -0.28
    çłĶåѦ
    -0.26
    èĥ¸åīį
    -0.26
    çļĦå¿ĥ
    -0.24
    磫
    -0.24
    èĩªé©¾
    -0.24
    ãģijãĤĭ
    -0.24
    /Sub
    -0.24
    POSITIVE LOGITS
    å¼ĢäºĨ
    0.27
    å¯ĨåĪĩ
    0.27
    UEL
    0.25
    .FILL
    0.25
    oric
    0.25
    ramework
    0.25
     Warfare
    0.25
    ceph
    0.25
    주
    0.24
    mps
    0.24
    Act Density 0.039%

    No Known Activations