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

    Neuronpedia

    INDEX
    Explanations

    Python code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     burning
    -0.06
    'em
    -0.06
    -0.06
    -0.06
    겼
    -0.06
     molest
    -0.06
     Δη
    -0.06
    	load
    -0.06
    kart
    -0.06
     люб
    -0.06
    POSITIVE LOGITS
    Contract
    0.07
    XB
    0.06
    rve
    0.06
     transparent
    0.06
     smuggling
    0.06
    verb
    0.06
    .lastIndexOf
    0.06
     FR
    0.06
     Som
    0.06
     نام
    0.06
    Act Density 0.077%

    No Known Activations