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

    Neuronpedia

    INDEX
    Explanations

    links to learning resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ogl
    0.42
    観光
    0.41
     ogr
    0.40
     Bc
    0.39
     Warren
    0.39
     ok
    0.38
     Karte
    0.38
    조
    0.37
    FormControl
    0.37
    সং
    0.37
    POSITIVE LOGITS
     المعد
    0.40
    herd
    0.37
     bombardment
    0.36
    머니
    0.36
    employees
    0.36
    debris
    0.36
    ieron
    0.36
    stage
    0.35
    groups
    0.34
     debris
    0.34
    Act Density 0.001%

    No Known Activations