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

    Neuronpedia

    INDEX
    Explanations

    day

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rewards
    -0.07
    .stage
    -0.07
     yardım
    -0.07
    .getData
    -0.07
     welcomed
    -0.07
    /pp
    -0.07
    grid
    -0.06
     Paul
    -0.06
    model
    -0.06
    <pcl
    -0.06
    POSITIVE LOGITS
     Ferr
    0.07
     elastic
    0.06
     BMC
    0.06
    엔
    0.06
    例
    0.06
     神马
    0.06
    _lead
    0.06
     شمالی
    0.06
    Tam
    0.06
     McMaster
    0.06
    Act Density 0.008%

    No Known Activations