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

    Neuronpedia

    INDEX
    Explanations

    assignment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    entered
    -0.08
    asonic
    -0.07
     gurl
    -0.07
     हवा
    -0.07
    -headed
    -0.07
    SA
    -0.07
    ವರು
    -0.07
    Drag
    -0.07
    Alarm
    -0.07
    visions
    -0.07
    POSITIVE LOGITS
     undertaken
    0.11
     pendiente
    0.09
    /questions
    0.08
     expressing
    0.08
     사항
    0.08
    -solving
    0.08
    /question
    0.08
     mindset
    0.08
     الدراسي
    0.07
    stellungen
    0.07
    Act Density 0.016%

    No Known Activations