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

    Neuronpedia

    INDEX
    Explanations

    chip

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	dd
    -0.07
    ramework
    -0.07
     cargo
    -0.06
    يلي
    -0.06
    architecture
    -0.06
     �
    -0.06
     ###
    -0.06
     duygu
    -0.06
     Vác
    -0.06
    orde
    -0.06
    POSITIVE LOGITS
     ejac
    0.07
     IC
    0.07
     oral
    0.07
    .Act
    0.06
     Alpine
    0.06
     impres
    0.06
     coins
    0.06
     diving
    0.06
     represents
    0.06
     sting
    0.06
    Act Density 0.010%

    No Known Activations