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

    Neuronpedia

    INDEX
    Explanations

    biggest

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    utschen
    -0.06
     Survival
    -0.06
    Ne
    -0.06
    افية
    -0.06
    vá
    -0.06
     výrob
    -0.06
    ambiguous
    -0.06
    оск
    -0.06
     repetition
    -0.06
     Sudoku
    -0.06
    POSITIVE LOGITS
     op
    0.07
     Ashton
    0.07
    (ray
    0.06
     رابط
    0.06
     spol
    0.06
    (codec
    0.06
     옆
    0.06
    .direction
    0.06
    (sym
    0.06
     öldür
    0.06
    Act Density 0.003%

    No Known Activations