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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Trung
    -0.07
     goed
    -0.07
     불
    -0.07
    ève
    -0.07
    cee
    -0.06
     controls
    -0.06
    ّل
    -0.06
     diary
    -0.06
     traps
    -0.06
     ventilation
    -0.06
    POSITIVE LOGITS
    	i
    0.06
     Align
    0.06
     poised
    0.06
     resigned
    0.06
     расход
    0.06
     Ре
    0.06
    انگلیسی
    0.06
     Buckingham
    0.06
    arro
    0.06
    flen
    0.05
    Act Density 0.009%

    No Known Activations