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

    Neuronpedia

    INDEX
    Explanations

    template usage

    np_max-act-logits · gemini-2.0-flashTriggered by @majianfei030706
    New Auto-Interp
    Negative Logits
    治好
    -0.07
     meno
    -0.07
     Lopez
    -0.07
     pulled
    -0.07
     más
    -0.07
    	Py
    -0.07
    	strncpy
    -0.07
     Scha
    -0.07
    ance
    -0.07
     hắn
    -0.07
    POSITIVE LOGITS
    ද
    0.08
    udades
    0.07
    ولات
    0.07
     cyclist
    0.07
     FPS
    0.07
    imd
    0.07
    enticate
    0.07
    צב
    0.07
     competitiveness
    0.07
    acteria
    0.07
    Act Density 0.000%

    No Known Activations