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

    Neuronpedia

    INDEX
    Explanations

    size

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ibu
    -0.06
    _STATUS
    -0.06
    _o
    -0.06
    .Message
    -0.06
    ijing
    -0.06
     Desired
    -0.06
     Startup
    -0.06
    _rel
    -0.06
     buff
    -0.05
    ´t
    -0.05
    POSITIVE LOGITS
     →↵↵
    0.07
    "}>↵
    0.07
    》
    0.07
     chaired
    0.07
    サー
    0.07
     обнаруж
    0.07
     compartments
    0.07
     ${↵
    0.07
     technique
    0.06
     Practice
    0.06
    Act Density 0.020%

    No Known Activations