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

    Neuronpedia

    INDEX
    Explanations

    future predictions and findings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dissident
    0.39
     yard
    0.36
     акы
    0.36
     tros
    0.36
     हे
    0.36
     უფ
    0.36
     dissidents
    0.36
                              
    0.36
     unenforceable
    0.36
    ន
    0.36
    POSITIVE LOGITS
     액세
    0.42
    uct
    0.40
     Sony
    0.40
    iect
    0.39
    ulent
    0.38
    acions
    0.38
    áv
    0.38
    sony
    0.38
     compi
    0.38
    ಬೇಕ
    0.37
    Act Density 0.000%

    No Known Activations