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

    Neuronpedia

    INDEX
    Explanations

    instanceof

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    你们
    -0.07
     BET
    -0.07
    itation
    -0.06
     going
    -0.06
     Dir
    -0.06
    528
    -0.06
    led
    -0.06
    _get
    -0.06
     Champions
    -0.06
    LineEdit
    -0.06
    POSITIVE LOGITS
    模式
    0.07
     sonuc
    0.07
    eden
    0.07
    (mut
    0.06
     professions
    0.06
    依
    0.06
    ={[↵
    0.06
     Tattoo
    0.06
    áj
    0.06
    ，↵
    0.06
    Act Density 0.002%

    No Known Activations