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

    Neuronpedia

    INDEX
    Explanations

    more

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mə
    -0.10
    heids
    -0.08
    akeng
    -0.08
    Everyone
    -0.08
     అన్ని
    -0.08
    мыс
    -0.08
    Every
    -0.07
    -style
    -0.07
     기타
    -0.07
     goûts
    -0.07
    POSITIVE LOGITS
     than
    0.09
     nữa
    0.08
    Than
    0.08
    _than
    0.08
     herm
    0.08
     niż
    0.08
     procent
    0.08
    _binary
    0.08
     decât
    0.08
     remarkable
    0.08
    Act Density 0.034%

    No Known Activations