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

    Neuronpedia

    INDEX
    Explanations

    ('<

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Message
    -0.08
    Once
    -0.07
    agements
    -0.07
     xmlDoc
    -0.07
    hift
    -0.07
     międzynarodow
    -0.07
     IDS
    -0.07
    Nib
    -0.07
    _ads
    -0.07
    senal
    -0.07
    POSITIVE LOGITS
    抗疫
    0.08
    HK
    0.08
    값
    0.07
    vi
    0.07
     purchasing
    0.07
    ponder
    0.07
    善良
    0.07
    チュ
    0.07
    大地
    0.07
     chống
    0.07
    Act Density 0.005%

    No Known Activations