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

    Neuronpedia

    INDEX
    Explanations

    Finding the key information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     approaches
    -0.08
     approached
    -0.08
    wn
    -0.08
     alternatives
    -0.08
    rc
    -0.07
     ähn
    -0.07
     embracing
    -0.07
     toy
    -0.07
    ugo
    -0.07
     deemed
    -0.07
    POSITIVE LOGITS
    Damit
    0.09
     tricky
    0.09
     Lies
    0.09
    Important
    0.08
     গুরুত্বপূর্ণ
    0.08
     থাকবে
    0.08
     Damit
    0.08
     Escape
    0.08
     Understand
    0.08
     verstehen
    0.08
    Act Density 0.025%

    No Known Activations