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

    Neuronpedia

    INDEX
    Explanations

    common english words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     logout
    -0.08
     swings
    -0.08
     fuels
    -0.08
     haine
    -0.08
     allerg
    -0.08
     providers
    -0.08
     allergens
    -0.08
     SUVs
    -0.08
     configur
    -0.08
     immun
    -0.08
    POSITIVE LOGITS
    算盘
    0.10
    Arithmetic
    0.10
    digits
    0.09
    -bin
    0.09
    Digits
    0.09
     digits
    0.09
     Arithmetic
    0.09
    九九
    0.08
     Instruction
    0.08
     Comput
    0.08
    Act Density 0.007%

    No Known Activations