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

    Neuronpedia

    INDEX
    Explanations

    delete unused files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mohabbat
    0.40
     deflation
    0.39
     pej
    0.39
     inflation
    0.38
     inflación
    0.38
     može
    0.37
    総合
    0.37
     může
    0.36
    䀎
    0.36
    ᒋ
    0.35
    POSITIVE LOGITS
    Learn
    0.46
    一顆
    0.44
    Each
    0.44
    Throughout
    0.44
     Learn
    0.44
     Each
    0.44
     Discount
    0.43
     дол
    0.42
     Put
    0.42
     Find
    0.42
    Act Density 0.000%

    No Known Activations