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

    Neuronpedia

    INDEX
    Explanations

    punctuation and stopwords

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _MODULES
    -0.08
    CHKERRQ
    -0.07
    jsonData
    -0.07
     Hải
    -0.07
     mating
    -0.07
    čan
    -0.07
    っち
    -0.06
     tutar
    -0.06
     thật
    -0.06
     Monetary
    -0.06
    POSITIVE LOGITS
     enhances
    0.07
    -fixed
    0.07
     attaching
    0.06
     reviewing
    0.06
     Backpack
    0.06
    ASA
    0.06
    _drive
    0.06
    getData
    0.06
     confirm
    0.06
    Captain
    0.06
    Act Density 0.000%

    No Known Activations