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

    Neuronpedia

    INDEX
    Explanations

    time/date stamp delimiters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    พา
    -0.07
    怫
    -0.07
    Batman
    -0.06
     wxString
    -0.06
    匝
    -0.06
     LSM
    -0.06
    pert
    -0.06
    -moving
    -0.06
    Leo
    -0.06
     boasting
    -0.06
    POSITIVE LOGITS
    而不
    0.07
    commended
    0.07
    作品内容
    0.07
     السياس
    0.07
     Plan
    0.07
    PLAY
    0.07
     personalize
    0.07
    固定的
    0.07
    筑
    0.06
    يات
    0.06
    Act Density 0.005%

    No Known Activations