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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mixture
    -0.07
    ixture
    -0.07
     RequestMethod
    -0.06
    "That
    -0.06
    杂
    -0.06
    easy
    -0.06
     commonplace
    -0.06
     setback
    -0.06
    Which
    -0.06
    spin
    -0.06
    POSITIVE LOGITS
    _fb
    0.07
    (char
    0.07
     każ
    0.07
    uyen
    0.06
    	char
    0.06
     unset
    0.06
     electrical
    0.06
     fright
    0.06
     ach
    0.06
    .colors
    0.06
    Act Density 0.010%

    No Known Activations