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

    Neuronpedia

    INDEX
    Explanations

    expressions of feelings/knowledge

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Coral
    -0.06
     Loose
    -0.06
     Sebastian
    -0.06
    TableCell
    -0.06
     McCoy
    -0.06
    钢
    -0.06
    /constants
    -0.06
     khóa
    -0.06
    /The
    -0.06
     ncols
    -0.06
    POSITIVE LOGITS
     ����
    0.07
    >'
↵
    0.06
     budete
    0.06
    -support
    0.06
    _chance
    0.06
    *cos
    0.06
    _cam
    0.06
    aidu
    0.06
     lf
    0.06
    	 ↵
    0.06
    Act Density 0.290%

    No Known Activations