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

    Neuronpedia

    INDEX
    Explanations

    Foundation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     curs
    -0.06
     langue
    -0.06
    �s
    -0.06
    _Field
    -0.06
     politely
    -0.06
     getStatus
    -0.06
    029
    -0.05
     mell
    -0.05
     foll
    -0.05
    /File
    -0.05
    POSITIVE LOGITS
     Sunderland
    0.17
     Titanic
    0.13
     Darth
    0.07
    nc
    0.07
    nik
    0.07
     Sith
    0.07
    inbox
    0.07
    ινε
    0.07
    历
    0.07
    ASCII
    0.07
    Act Density 0.002%

    No Known Activations