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

    Neuronpedia

    INDEX
    Explanations

    Notifications and alerts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <cv
    -0.08
    (sm
    -0.07
    posição
    -0.07
    (Sprite
    -0.07
    Persist
    -0.07
     שק
    -0.07
    倏
    -0.07
    伺
    -0.07
    (ps
    -0.07
     prosecuted
    -0.06
    POSITIVE LOGITS
     Ner
    0.08
    文体
    0.07
    ↵↵    ↵
    0.07
    .band
    0.07
     overloaded
    0.07
    �
    0.07
      ↵↵↵
    0.07
    adian
    0.06
    我要
    0.06
    饰品
    0.06
    Act Density 0.047%

    No Known Activations