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

    Neuronpedia

    INDEX
    Explanations

    not to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UFF
    -0.07
     Hardy
    -0.06
    "+↵
    -0.06
     міжнарод
    -0.06
    ervisor
    -0.06
     Worse
    -0.06
     قرارد
    -0.06
    $item
    -0.06
    ankind
    -0.06
     humidity
    -0.06
    POSITIVE LOGITS
    Laugh
    0.09
    collect
    0.09
     crackdown
    0.08
     goalt
    0.07
    	Collection
    0.07
    _sequences
    0.07
    .newArrayList
    0.06
     disagreements
    0.06
     uncomment
    0.06
    _COMP
    0.06
    Act Density 0.002%

    No Known Activations