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

    Neuronpedia

    INDEX
    Explanations

    children

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gap
    -0.07
     Ars
    -0.06
     closet
    -0.06
     meille
    -0.06
     Vuex
    -0.06
    Software
    -0.06
    Asian
    -0.06
    τύ
    -0.06
     bustling
    -0.06
     Nurses
    -0.06
    POSITIVE LOGITS
    :\\
    0.07
    ursively
    0.07
     ping
    0.06
    济
    0.06
     şik
    0.06
     nikdy
    0.06
    ptron
    0.06
     children
    0.06
     hijos
    0.06
     acciones
    0.06
    Act Density 0.020%

    No Known Activations