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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     penny
    -0.07
    =='
    -0.07
    ???
    -0.07
     llegar
    -0.07
    ès
    -0.07
    勤
    -0.06
     потер
    -0.06
    +"/
    -0.06
     bras
    -0.06
     보고
    -0.06
    POSITIVE LOGITS
    	cin
    0.06
    27
    0.06
    _W
    0.06
    :
↵
    0.06
    31
    0.06
     lizard
    0.06
    custom
    0.06
    (I
    0.05
     nxt
    0.05
     양
    0.05
    Act Density 0.000%

    No Known Activations