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

    Neuronpedia

    INDEX
    Explanations

    code comments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    “For
    -0.07
    qing
    -0.06
    도의
    -0.06
     wizards
    -0.06
     tougher
    -0.06
    -with
    -0.06
    .COMP
    -0.06
    кий
    -0.06
     expands
    -0.06
    /news
    -0.06
    POSITIVE LOGITS
    _payload
    0.07
     Nor
    0.06
     ут
    0.06
     kde
    0.06
     bidi
    0.06
    _disconnect
    0.06
     adb
    0.06
    Proof
    0.06
     edilir
    0.06
     Occ
    0.06
    Act Density 0.001%

    No Known Activations