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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     schwer
    -0.07
     zonder
    -0.06
    ühr
    -0.06
     known
    -0.06
    عمل
    -0.06
    March
    -0.06
     hanno
    -0.06
    _MAP
    -0.06
     flames
    -0.06
     rewriting
    -0.06
    POSITIVE LOGITS
     Českosloven
    0.07
    τευ
    0.07
    	Null
    0.06
     Helen
    0.06
    FI
    0.06
    (expect
    0.06
     Documentary
    0.06
     Incoming
    0.06
     ΚΑΙ
    0.06
    Resize
    0.06
    Act Density 0.122%

    No Known Activations