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

    Neuronpedia

    INDEX
    Explanations

    physical, professional, powder

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zah
    0.44
    ignored
    0.36
     filtrate
    0.36
    籿
    0.36
    qid
    0.36
    spare
    0.35
    zicht
    0.35
     продажи
    0.35
    apo
    0.35
    not
    0.34
    POSITIVE LOGITS
    illes
    0.39
    Ꮋ
    0.38
    insen
    0.38
    ➁
    0.38
     Normand
    0.38
    NP
    0.38
     Optionally
    0.38
     including
    0.38
     replying
    0.38
     acquiring
    0.37
    Act Density 0.001%

    No Known Activations