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

    Neuronpedia

    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	open
    -0.07
    еть
    -0.07
    eldig
    -0.06
    _EDGE
    -0.06
    .VISIBLE
    -0.06
    modules
    -0.06
    损
    -0.06
     Balt
    -0.06
     چرا
    -0.06
    .Lines
    -0.06
    POSITIVE LOGITS
    863
    0.07
    .djang
    0.06
     errorThrown
    0.06
     objedn
    0.06
     방송
    0.06
    ícul
    0.06
    lacağ
    0.06
    _SYMBOL
    0.06
    δος
    0.06
    asticsearch
    0.06
    Act Density 0.017%

    No Known Activations