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

    Neuronpedia

    INDEX
    Explanations

    family

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Authorized
    -0.08
     par
    -0.08
     expire
    -0.07
     hanya
    -0.07
     grande
    -0.07
     br
    -0.07
    ================================================================
    -0.07
    ろう
    -0.07
     Rational
    -0.07
     расс
    -0.07
    POSITIVE LOGITS
    _KeyPress
    0.07
    ession
    0.07
     CheckBox
    0.07
    /Subthreshold
    0.07
    often
    0.07
    美好生活
    0.07
    Maps
    0.07
     בשבוע
    0.07
     üyeler
    0.07
     meisjes
    0.07
    Act Density 0.004%

    No Known Activations