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

    Neuronpedia

    INDEX
    Explanations

    Technical/academic discussion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dél
    -0.07
     bunch
    -0.06
    ":
↵
    -0.06
    /bash
    -0.06
    .CurrentRow
    -0.06
     Rider
    -0.06
     večer
    -0.06
     역
    -0.06
     happened
    -0.06
    ').'
    -0.06
    POSITIVE LOGITS
     VERIFY
    0.07
    �다
    0.07
    _opt
    0.07
    ViewInit
    0.06
    碼
    0.06
    -www
    0.06
    �
    0.06
    CTIONS
    0.06
     obs
    0.06
     takeaway
    0.06
    Act Density 0.001%

    No Known Activations