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

    Neuronpedia

    INDEX
    Explanations

    Scientific references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    룹
    -0.07
    房间
    -0.07
    QN
    -0.07
    胸
    -0.07
     justifyContent
    -0.07
    win
    -0.07
    Jonathan
    -0.07
    smooth
    -0.07
    冲
    -0.06
    зм
    -0.06
    POSITIVE LOGITS
    _yield
    0.06
     특별
    0.06
     *}↵↵
    0.06
    (comb
    0.05
    	position
    0.05
    >I
    0.05
     Pacers
    0.05
    UILT
    0.05
    作为
    0.05
    _D
    0.05
    Act Density 0.011%

    No Known Activations