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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DEF
    -0.07
    Crypt
    -0.07
    	ERR
    -0.07
     Ingredients
    -0.06
    bond
    -0.06
    renderer
    -0.06
    errs
    -0.06
    dsa
    -0.06
    HexString
    -0.06
    232
    -0.06
    POSITIVE LOGITS
    ों
    0.07
     staggering
    0.07
    ，一
    0.06
     cao
    0.06
    ｀
    0.06
     lower
    0.06
    ("//
    0.06
     ман
    0.06
    UR
    0.06
    ौं
    0.06
    Act Density 0.052%

    No Known Activations