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

    Neuronpedia

    INDEX
    Explanations

    News articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    b
    -0.08
    _NB
    -0.07
    両
    -0.07
     radix
    -0.06
    iado
    -0.06
    Pub
    -0.06
     t�
    -0.06
     Dise
    -0.06
     emerging
    -0.06
     clouds
    -0.06
    POSITIVE LOGITS
     kern
    0.08
    ��이지
    0.07
     EMAIL
    0.06
    три
    0.06
    ,nonatomic
    0.06
    COMMENT
    0.06
    [↵
    0.06
     prank
    0.06
    da
    0.06
    	login
    0.06
    Act Density 0.005%

    No Known Activations