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

    Neuronpedia

    INDEX
    Explanations

    business products services

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    3
    -0.07
    6
    -0.07
    4
    -0.07
    停产
    -0.07
     togg
    -0.07
     sentimental
    -0.07
    要注意
    -0.06
    balanced
    -0.06
     fontsize
    -0.06
    features
    -0.06
    POSITIVE LOGITS
    ↵↵
    0.11
    .↵↵
    0.11
    .↵
    0.11
    。↵
    0.10
    ?↵↵
    0.10
    .
    0.10
    )↵
    0.09
    ↵
    0.08
    )
↵
    0.08
    )↵↵
    0.08
    Act Density 21.700%

    No Known Activations