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

    Neuronpedia

    INDEX
    Explanations

    I

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _DBG
    -0.07
     State
    -0.07
    .all
    -0.06
     Colonel
    -0.06
    Metadata
    -0.06
     occupies
    -0.06
     cowboy
    -0.06
    Newton
    -0.06
     Wellington
    -0.06
     Upper
    -0.06
    POSITIVE LOGITS
     powering
    0.07
    ifik
    0.07
    (){↵↵
    0.07
     '')↵↵
    0.07
    ีอ
    0.06
    azioni
    0.06
     期
    0.06
    تیب
    0.06
    GUID
    0.06
     дані
    0.06
    Act Density 0.075%

    No Known Activations