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

    Neuronpedia

    INDEX
    Explanations

    playback control

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Recipient
    0.39
    mente
    0.39
    den
    0.37
    Questa
    0.37
    Historically
    0.36
    result
    0.36
    nl
    0.36
    íticas
    0.36
    ünschen
    0.36
     странице
    0.36
    POSITIVE LOGITS
     played
    0.43
     triglyceride
    0.42
     ballet
    0.39
     watch
    0.37
     watches
    0.36
     Ayurvedic
    0.36
     handicrafts
    0.35
     halibut
    0.35
     biodegradation
    0.35
     spielte
    0.35
    Act Density 0.001%

    No Known Activations