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

    Neuronpedia

    INDEX
    Explanations

    stolen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	cal
    -0.07
     القرن
    -0.07
    ivate
    -0.06
     таким
    -0.06
    程序
    -0.06
    buffers
    -0.06
    .Marker
    -0.06
    angible
    -0.06
     Prop
    -0.06
    etrics
    -0.06
    POSITIVE LOGITS
     stolen
    0.11
     सम
    0.07
    0.07
    -----
    0.06
     Dylan
    0.06
     electricity
    0.06
     کار
    0.06
     pis
    0.06
    ↓
    0.06
    сих
    0.06
    Act Density 0.004%

    No Known Activations