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

    Neuronpedia

    INDEX
    Explanations

    Code examples

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pring
    -0.07
    ᛁ
    -0.07
    วร
    -0.07
    rib
    -0.07
    >_
    -0.07
    .getNode
    -0.07
    رص
    -0.06
    מח
    -0.06
     criminal
    -0.06
    专线
    -0.06
    POSITIVE LOGITS
     eslint
    0.07
     Lad
    0.07
    票
    0.07
     mum
    0.07
     catches
    0.07
    Patrick
    0.07
    uelle
    0.07
     Barry
    0.06
    ？↵↵
    0.06
    担负
    0.06
    Act Density 0.057%

    No Known Activations