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

    Neuronpedia

    INDEX
    Explanations

    occasional

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sommes
    -0.07
    䗛
    -0.07
    hôtel
    -0.07
    ʊ
    -0.07
     Winners
    -0.06
     hướng
    -0.06
    ɪ
    -0.06
    等一系列
    -0.06
    atinum
    -0.06
    _TOUCH
    -0.06
    POSITIVE LOGITS
    电解
    0.07
    Scalar
    0.07
     `.
    0.07
    .TextAlignment
    0.07
    registration
    0.07
     intermittent
    0.07
    Executable
    0.07
    窖
    0.06
     shear
    0.06
    -bal
    0.06
    Act Density 0.004%

    No Known Activations