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

    Neuronpedia

    INDEX
    Explanations

    clarifying specific ideas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     reso
    0.52
    cza
    0.47
     qualifies
    0.46
     avendo
    0.46
    contentInset
    0.45
     teniendo
    0.45
    cón
    0.45
     negociación
    0.45
     parcours
    0.45
     ponctués
    0.45
    POSITIVE LOGITS
     Implement
    0.51
    Storage
    0.49
    Implement
    0.49
     Within
    0.49
     Scrap
    0.48
     Slack
    0.47
    Online
    0.46
     Feeling
    0.46
     Utt
    0.45
     Online
    0.45
    Act Density 0.000%

    No Known Activations