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

    Neuronpedia

    INDEX
    Explanations

    converter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (it
    -0.07
     PropertyValue
    -0.06
    polit
    -0.06
     xp
    -0.06
    278
    -0.06
     Gret
    -0.06
    --------------------------------------------------------------------------------
    -0.06
    	gl
    -0.06
    	wait
    -0.06
    tout
    -0.06
    POSITIVE LOGITS
    σεις
    0.07
     uygulama
    0.07
     engages
    0.07
     Cuban
    0.07
    ользов
    0.07
    _Index
    0.06
    ồ
    0.06
     Aless
    0.06
     ofApp
    0.06
    にと
    0.06
    Act Density 0.007%

    No Known Activations