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

    Neuronpedia

    INDEX
    Explanations

    Time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ài
    -0.07
    她
    -0.07
    िसम
    -0.06
    бира
    -0.06
     expects
    -0.06
    invest
    -0.06
    anging
    -0.06
    armacy
    -0.06
     monk
    -0.06
    	answer
    -0.06
    POSITIVE LOGITS
    (pointer
    0.07
    udden
    0.07
     coherence
    0.07
    Filename
    0.06
     EditorGUI
    0.06
    lluminate
    0.06
     ole
    0.06
    /cgi
    0.06
     Sergeant
    0.06
     Automatic
    0.06
    Act Density 0.003%

    No Known Activations