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

    Neuronpedia

    INDEX
    Explanations

    Facial features

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     offenders
    -0.07
     Roth
    -0.07
     witch
    -0.06
    _argument
    -0.06
    angep
    -0.06
    etin
    -0.06
    },"
    -0.06
     Kennedy
    -0.06
    optic
    -0.06
     Tx
    -0.06
    POSITIVE LOGITS
    τηγορία
    0.07
    ALCHEMY
    0.07
    craper
    0.07
    ASCII
    0.07
     نمودار
    0.07
    ائمة
    0.06
     ตำ
    0.06
    wide
    0.06
    [Unit
    0.06
    .／
    0.06
    Act Density 0.017%

    No Known Activations