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

    Neuronpedia

    INDEX
    Explanations

    preferably

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .combine
    -0.06
     discovered
    -0.06
    NC
    -0.06
     دوست
    -0.06
     adventurous
    -0.06
     Tall
    -0.06
    漫
    -0.06
     alterations
    -0.06
     tells
    -0.06
     splits
    -0.06
    POSITIVE LOGITS
     preferably
    0.08
     ideally
    0.08
    symbols
    0.08
     Ideally
    0.08
     Naples
    0.07
    差
    0.07
    icularly
    0.07
     axes
    0.07
    !");↵
    0.06
     �
    0.06
    Act Density 0.004%

    No Known Activations