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

    Neuronpedia

    INDEX
    Explanations

    she/her

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ethe
    -0.07
     Zar
    -0.07
    CHILD
    -0.06
    Detailed
    -0.06
    Entered
    -0.06
    ','=','
    -0.06
     jav
    -0.06
     Constraints
    -0.06
     detailed
    -0.06
    .xticks
    -0.06
    POSITIVE LOGITS
     spaceship
    0.07
     зменш
    0.07
    (QStringLiteral
    0.06
     нерв
    0.06
    gles
    0.06
    belongs
    0.06
    anya
    0.06
    用户
    0.06
     GROUP
    0.06
     başk
    0.06
    Act Density 1.617%

    No Known Activations