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

    Neuronpedia

    INDEX
    Explanations

    women

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -import
    -0.07
    PP
    -0.06
     adoption
    -0.06
    orners
    -0.06
     �
    -0.06
    �
    -0.06
    GENER
    -0.06
    679
    -0.06
    γχ
    -0.06
     emperor
    -0.06
    POSITIVE LOGITS
     bunch
    0.07
     clearTimeout
    0.07
     Colo
    0.06
    atial
    0.06
     sûr
    0.06
     mohl
    0.06
     TRACK
    0.06
    .habbo
    0.06
    .Entities
    0.06
    andes
    0.06
    Act Density 0.239%

    No Known Activations