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

    Neuronpedia

    INDEX
    Explanations

    Code and text strings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    endant
    -0.07
    ules
    -0.07
     sıcak
    -0.07
     lược
    -0.06
     staveb
    -0.06
    emonic
    -0.06
     kardeş
    -0.06
    ıyı
    -0.06
    _setting
    -0.06
     patience
    -0.06
    POSITIVE LOGITS
     Falcon
    0.07
    ounded
    0.07
    !).
    0.07
     recieved
    0.07
     record
    0.07
    Cfg
    0.07
     KV
    0.06
    breaking
    0.06
     Ravens
    0.06
    .getFullYear
    0.06
    Act Density 0.000%

    No Known Activations