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

    Neuronpedia

    INDEX
    Explanations

    summar

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /Application
    -0.07
    -input
    -0.06
    |wx
    -0.06
    zheimer
    -0.06
    odes
    -0.06
    /vendor
    -0.06
    pread
    -0.06
    WhiteSpace
    -0.06
    _old
    -0.06
     reopening
    -0.06
    POSITIVE LOGITS
    (LOG
    0.07
     kn
    0.07
     Nisan
    0.07
    ').↵
    0.07
     ''↵↵
    0.06
     slamming
    0.06
    .")
↵
    0.06
    Rem
    0.06
     Dwarf
    0.06
    ’.↵↵
    0.06
    Act Density 0.005%

    No Known Activations