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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ranged
    -0.07
    烧
    -0.06
     davon
    -0.06
    emales
    -0.06
     Tb
    -0.06
     procession
    -0.06
     باب
    -0.06
    ।↵↵
    -0.06
     тка
    -0.06
     further
    -0.06
    POSITIVE LOGITS
    	JOptionPane
    0.06
    Lie
    0.06
     hexadecimal
    0.06
     discour
    0.06
    TokenType
    0.06
    Water
    0.06
    ndon
    0.06
    těz
    0.06
     Emp
    0.06
    зації
    0.06
    Act Density 0.000%

    No Known Activations