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

    Neuronpedia

    INDEX
    Explanations

    here are a few

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ційних
    0.42
     Sett
    0.40
     prestación
    0.40
     debes
    0.40
     ingeniero
    0.40
     prestazioni
    0.39
     millioner
    0.39
     itinéraires
    0.39
    olisme
    0.39
     Maurizio
    0.38
    POSITIVE LOGITS
     article
    0.39
     recreated
    0.39
     short
    0.37
     dense
    0.36
     gathered
    0.36
     Short
    0.35
    mp
    0.35
    article
    0.35
    uffles
    0.35
     document
    0.34
    Act Density 0.001%

    No Known Activations