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

    Neuronpedia

    INDEX
    Explanations

    ="

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Object
    -0.06
    468
    -0.06
    bjerg
    -0.06
     fyz
    -0.06
    -middle
    -0.06
    sep
    -0.06
    ίν
    -0.06
    -CS
    -0.06
     мені
    -0.06
    Alamat
    -0.06
    POSITIVE LOGITS
    只是
    0.07
     subsequ
    0.07
    -security
    0.07
    0.06
    0.06
     exhilar
    0.06
     acct
    0.06
    	mysqli
    0.06
    `='$
    0.06
    roduce
    0.06
    Act Density 0.007%

    No Known Activations