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

    Neuronpedia

    INDEX
    Explanations

    -host

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (diff
    -0.07
    _folder
    -0.07
     potatoes
    -0.06
    _picker
    -0.06
     launch
    -0.06
     laid
    -0.06
    _statuses
    -0.06
    .Restrict
    -0.06
    年代
    -0.06
    PB
    -0.06
    POSITIVE LOGITS
    гор
    0.07
     него
    0.06
    Fra
    0.06
    министра
    0.06
    ินค
    0.06
    长
    0.06
    -tools
    0.06
     fellow
    0.06
    сих
    0.06
     baker
    0.06
    Act Density 0.000%

    No Known Activations