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

    Neuronpedia

    INDEX
    Explanations

    fixing technical issues

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    etric
    -0.07
    abetic
    -0.06
    AT
    -0.06
    تح
    -0.06
     Stefan
    -0.06
    junction
    -0.06
     blasts
    -0.06
     Ideal
    -0.06
    ournament
    -0.06
    	timer
    -0.06
    POSITIVE LOGITS
     +
↵
    0.07
     straně
    0.07
     demographics
    0.07
    _authenticated
    0.07
     airl
    0.07
    .slides
    0.07
     =
↵
    0.06
     commod
    0.06
    ror
    0.06
    _SELECTOR
    0.06
    Act Density 0.030%

    No Known Activations