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

    Neuronpedia

    INDEX
    Explanations

    modelBuilder

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     сейчас
    -0.08
    Bus
    -0.07
    火
    -0.07
     Strong
    -0.07
    	case
    -0.06
     بايد
    -0.06
    ibe
    -0.06
    ibre
    -0.06
    KH
    -0.06
    _anim
    -0.06
    POSITIVE LOGITS
    converter
    0.07
    YNAMIC
    0.07
     구조
    0.07
    osition
    0.06
     yyn
    0.06
     demo
    0.06
     messageType
    0.06
     Fresno
    0.06
     chrono
    0.06
    urn
    0.06
    Act Density 0.008%

    No Known Activations