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

    Neuronpedia

    INDEX
    Explanations

    Technical/scientific text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gray
    -0.07
    ル
    -0.06
    reveal
    -0.06
     nine
    -0.06
    ise
    -0.06
    /preferences
    -0.06
    _ALIGNMENT
    -0.06
    -0.06
    대회
    -0.06
    エル
    -0.06
    POSITIVE LOGITS
    .delivery
    0.07
    _minute
    0.07
    (coll
    0.07
    .upper
    0.06
     davidjl
    0.06
    aaaa
    0.06
     reloc
    0.06
    (find
    0.06
    inished
    0.06
    inand
    0.06
    Act Density 0.534%

    No Known Activations