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

    Neuronpedia

    INDEX
    Explanations

    consequences/sequences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ertain
    -0.08
    αιν
    -0.08
     электр
    -0.07
     organs
    -0.07
    ','".$
    -0.07
    _ro
    -0.07
     open
    -0.07
     Detroit
    -0.07
    	open
    -0.07
     parl
    -0.07
    POSITIVE LOGITS
     consequences
    0.11
    sequences
    0.09
    lead
    0.07
    _messages
    0.06
     народу
    0.06
     Comment
    0.06
    _cons
    0.06
     keyst
    0.06
    iples
    0.06
    減
    0.06
    Act Density 0.013%

    No Known Activations