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

    Neuronpedia

    INDEX
    Explanations

    references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     phosphory
    -0.08
     collagen
    -0.07
    -force
    -0.07
    衝
    -0.07
    avian
    -0.07
     Trick
    -0.07
    inned
    -0.06
    中式
    -0.06
    ้อง
    -0.06
     Cheng
    -0.06
    POSITIVE LOGITS
    ‛
    0.08
    �
    0.07
    .bpm
    0.07
     Rihanna
    0.07
    _PROVID
    0.07
    買い物
    0.07
    Editors
    0.07
    宿迁
    0.07
    Reduc
    0.07
    .notifications
    0.06
    Act Density 0.043%

    No Known Activations