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

    Neuronpedia

    INDEX
    Explanations

    sentence fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     douche
    -0.07
    Move
    -0.07
    xcc
    -0.07
     góp
    -0.07
    fce
    -0.07
     σει
    -0.07
     सद
    -0.06
     buckle
    -0.06
    ţi
    -0.06
    sob
    -0.06
    POSITIVE LOGITS
     Tourism
    0.07
     critic
    0.07
     rarely
    0.06
     memset
    0.06
     станов
    0.06
    ुआ
    0.06
     scientific
    0.06
    %%%%%%%%%%%%%%%%
    0.06
    інг
    0.06
     BUT
    0.06
    Act Density 0.000%

    No Known Activations