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

    Neuronpedia

    INDEX
    Explanations

    convergence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     без
    -0.07
    انات
    -0.07
     dl
    -0.06
     sheriff
    -0.06
     Dover
    -0.06
     كتاب
    -0.06
    moved
    -0.06
    HEY
    -0.06
     школ
    -0.06
     Mash
    -0.06
    POSITIVE LOGITS
     پ
    0.07
    ;q
    0.07
    OMATIC
    0.07
    female
    0.06
    сол
    0.06
    	Q
    0.06
     چ
    0.06
     controller
    0.06
     birden
    0.06
     keyCode
    0.06
    Act Density 0.458%

    No Known Activations