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
     Jag
    -0.08
     Certification
    -0.07
     certifications
    -0.07
     tags
    -0.07
    decode
    -0.07
    _bed
    -0.07
    ample
    -0.07
    /lab
    -0.07
     quoting
    -0.07
    essed
    -0.06
    POSITIVE LOGITS
     domu
    0.06
    (ss
    0.06
    _OW
    0.06
     तर
    0.06
     рев
    0.06
    _seconds
    0.06
     Alic
    0.06
    /**/*.
    0.06
     loi
    0.06
     pathlib
    0.06
    Act Density 0.018%

    No Known Activations