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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ày
    -0.07
     Dann
    -0.07
    �
    -0.06
    ValueCollection
    -0.06
    ω
    -0.06
     zorunlu
    -0.06
    urst
    -0.06
     Richardson
    -0.06
     "@
    -0.06
    ۳۵
    -0.06
    POSITIVE LOGITS
     ↵
    0.07
    ：↵↵
    0.07
    ]↵↵
    0.07
     mirrors
    0.07
     osp
    0.07
    .
    0.06
    ）↵
    0.06
      ↵
    0.06
    eward
    0.06
     ]↵
    0.06
    Act Density 0.021%

    No Known Activations