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

    Neuronpedia

    INDEX
    Explanations

    be

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (insert
    -0.08
    PECT
    -0.07
    pect
    -0.06
    ۱۶
    -0.06
     Ele
    -0.06
    returns
    -0.06
    ۱۵
    -0.06
     yards
    -0.06
     Vampire
    -0.06
     TableName
    -0.06
    POSITIVE LOGITS
    closing
    0.07
    Tur
    0.07
    블
    0.06
    خت
    0.06
     idols
    0.06
    piel
    0.06
     광
    0.06
    ktop
    0.06
     قطر
    0.06
     กล
    0.06
    Act Density 0.000%

    No Known Activations