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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _comb
    -0.07
    ponses
    -0.07
    _room
    -0.06
    險
    -0.06
    iosity
    -0.06
     learns
    -0.06
    iap
    -0.06
    );?>↵
    -0.06
     Edge
    -0.06
    _upload
    -0.06
    POSITIVE LOGITS
    援
    0.07
    ılacak
    0.06
     Telescope
    0.06
     embark
    0.06
    Affected
    0.06
     embarked
    0.06
    arking
    0.06
    人間
    0.06
     farming
    0.06
    ocious
    0.06
    Act Density 0.056%

    No Known Activations