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

    Neuronpedia

    INDEX
    Explanations

    the hotline

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     아마
    0.42
     Lover
    0.38
     Ahead
    0.37
    安全的
    0.37
     phận
    0.37
     unst
    0.36
     dol
    0.36
     franc
    0.36
    lemagne
    0.36
    earance
    0.35
    POSITIVE LOGITS
    riu
    0.40
    svet
    0.40
    Sun
    0.39
    <unused16>
    0.39
    reib
    0.38
    missione
    0.38
    Rubber
    0.38
    dreams
    0.38
    stroke
    0.38
    Rek
    0.38
    Act Density 0.002%

    No Known Activations