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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    los
    -0.07
    itations
    -0.07
     harbour
    -0.07
     nests
    -0.07
    }>
    -0.07
    infer
    -0.06
    '"
    -0.06
    '>
    -0.06
     hra
    -0.06
    Choices
    -0.06
    POSITIVE LOGITS
     dors
    0.06
    .CommandType
    0.06
    .opt
    0.06
     المغرب
    0.06
     изображ
    0.06
    .enum
    0.05
     Attendance
    0.05
    .ec
    0.05
    .Expression
    0.05
    /*@
    0.05
    Act Density 0.025%

    No Known Activations