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

    Neuronpedia

    INDEX
    Explanations

    humor and jokes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ted
    -0.07
    ік
    -0.07
    .Security
    -0.07
     translates
    -0.07
    essions
    -0.06
     Wheeler
    -0.06
     bbc
    -0.06
    .LocalDateTime
    -0.06
     Sailor
    -0.06
     jt
    -0.06
    POSITIVE LOGITS
     آذ
    0.07
    งม
    0.06
     μεγ
    0.06
     strtok
    0.06
    лан
    0.06
     vendor
    0.06
    철
    0.06
     Autor
    0.06
    uli
    0.06
    وار
    0.06
    Act Density 0.022%

    No Known Activations