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

    Neuronpedia

    INDEX
    Explanations

    Code/technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .MEDIA
    -0.07
     podí
    -0.07
    WithValue
    -0.06
    jiang
    -0.06
    เทพ
    -0.06
    Quality
    -0.06
     程
    -0.06
    ematics
    -0.06
    شم
    -0.06
    urses
    -0.06
    POSITIVE LOGITS
    ("/")↵
    0.06
    .address
    0.06
     rp
    0.06
     distinction
    0.06
     elim
    0.06
    ，一
    0.06
    日に
    0.06
     وم
    0.06
     "),
    0.06
     ✓
    0.06
    Act Density 0.357%

    No Known Activations