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

    Neuronpedia

    INDEX
    Explanations

    MIDI, posture

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    es
    0.94
    al
    0.91
    LLY
    0.86
    et
    0.86
    root
    0.85
    as
    0.84
    el
    0.82
    edges
    0.82
    ed
    0.81
    squiggle
    0.81
    POSITIVE LOGITS
    е
    1.12
     сатып
    0.96
     ilişkin
    0.95
     dotycz
    0.94
    о
    0.93
    ள்ளார்
    0.92
     rozwo
    0.91
     Außerdem
    0.91
     niiden
    0.91
    েনার
    0.89
    Act Density 0.003%

    No Known Activations