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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Morton
    -0.07
    eba
    -0.07
     invoked
    -0.07
     Andre
    -0.07
    daemon
    -0.07
    .GetKey
    -0.07
    κτη
    -0.07
    authorization
    -0.06
     Algorithms
    -0.06
    quires
    -0.06
    POSITIVE LOGITS
    
↵
    0.07
     ＼↵
    0.06
    =?",
    0.06
    PED
    0.06
    ＼↵
    0.06
    horia
    0.06
    ↵                    ↵
    0.06
    ','');↵
    0.06
     ],↵
    0.06
    _DIGEST
    0.06
    Act Density 0.006%

    No Known Activations