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

    Neuronpedia

    INDEX
    Explanations

    specific tokens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    in
    0.60
     Winf
    0.49
    un
    0.49
    yní
    0.49
    string
    0.46
    err
    0.45
    die
    0.43
    úrate
    0.43
    Juris
    0.43
     Öz
    0.43
    POSITIVE LOGITS
     bulbs
    0.49
     eateries
    0.49
     coalgebras
    0.49
     effluents
    0.49
     mesons
    0.48
     globules
    0.48
     hadrons
    0.48
     solutes
    0.48
     nitrates
    0.48
     institutes
    0.47
    Act Density 0.009%

    No Known Activations