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

    Neuronpedia

    INDEX
    Explanations

    jsonplaceholder.typicode.com URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fire
    0.68
     suggested
    0.66
     worth
    0.65
     payable
    0.65
     skirt
    0.63
     getting
    0.63
     comprehension
    0.62
     pulled
    0.62
    ,
    0.62
     stuck
    0.62
    POSITIVE LOGITS
    ㅀ
    0.88
    ggbb
    0.87
    layoutWidget
    0.83
    itorios
    0.82
    typicode
    0.81
    xticks
    0.80
     '<%=
    0.77
    ffffff
    0.77
    èlement
    0.76
    urbance
    0.76
    Act Density 0.002%

    No Known Activations