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
    ��
    -0.07
     predictor
    -0.07
    適
    -0.07
    ASF
    -0.06
    (Sql
    -0.06
     مساحت
    -0.06
     SST
    -0.06
     \"{
    -0.06
    نه
    -0.06
    ，比
    -0.06
    POSITIVE LOGITS
    369
    0.06
    aternity
    0.06
    501
    0.06
    }))↵↵
    0.06
     aberr
    0.06
     proposition
    0.06
     whistlebl
    0.06
     TOD
    0.06
    包含
    0.06
     γυνα
    0.06
    Act Density 0.001%

    No Known Activations