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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     build
    -0.07
    _part
    -0.07
    raits
    -0.07
     money
    -0.07
     Со
    -0.07
    小
    -0.07
     fire
    -0.07
    posure
    -0.07
     leaking
    -0.06
    比
    -0.06
    POSITIVE LOGITS
    CMP
    0.07
     serv
    0.06
     Tolkien
    0.06
     subscri
    0.06
     onFocus
    0.06
    elenium
    0.06
     Academ
    0.06
     ['.
    0.06
    .EditorButton
    0.06
     підстав
    0.06
    Act Density 0.152%

    No Known Activations