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

    Neuronpedia

    INDEX
    Explanations

    code styling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "M
    -0.08
    _lists
    -0.06
    英文
    -0.06
    841
    -0.06
    journal
    -0.06
    alim
    -0.06
     mqtt
    -0.06
    github
    -0.06
     Vere
    -0.06
     hakk
    -0.06
    POSITIVE LOGITS
     indulge
    0.07
    /"↵↵
    0.07
     ロ
    0.07
    頂
    0.06
     addChild
    0.06
    etable
    0.06
     schedule
    0.06
     proofs
    0.06
     poverty
    0.06
    �
    0.06
    Act Density 0.022%

    No Known Activations