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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ه
    -0.07
    _CLEAR
    -0.07
     LinearGradient
    -0.07
    .ImageAlign
    -0.07
     пох
    -0.06
     accusing
    -0.06
     ero
    -0.06
     incel
    -0.06
     SLOT
    -0.06
    め
    -0.06
    POSITIVE LOGITS
    /linux
    0.06
    _addresses
    0.06
    ramer
    0.06
     cups
    0.06
     speaking
    0.06
    ฉ
    0.06
     Carson
    0.06
    _token
    0.06
    /item
    0.06
    ूसर
    0.06
    Act Density 0.000%

    No Known Activations