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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     presidential
    -0.08
    YLeaf
    -0.07
     datetime
    -0.07
    Ⴆ
    -0.07
     advertisement
    -0.06
     brave
    -0.06
    _DF
    -0.06
    -0.06
    已久
    -0.06
    右
    -0.06
    POSITIVE LOGITS
     see
    0.07
    ✧
    0.06
     glitch
    0.06
     Hopkins
    0.06
     серии
    0.06
     cognitive
    0.06
    山寨
    0.06
     slower
    0.06
     рождения
    0.06
    區
    0.06
    Act Density 0.013%

    No Known Activations