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

    Neuronpedia

    INDEX
    Explanations

    8

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cabinets
    -0.07
    .LocalDateTime
    -0.06
     instantaneous
    -0.06
     defined
    -0.06
     Yemen
    -0.06
    (auto
    -0.06
     grease
    -0.06
     transporter
    -0.06
    oyal
    -0.06
    .partition
    -0.06
    POSITIVE LOGITS
    finding
    0.06
    ewitness
    0.06
    азвание
    0.06
     fieldName
    0.06
     клі
    0.06
    "text
    0.06
    bomb
    0.06
    �
    0.06
    紹
    0.06
    ských
    0.06
    Act Density 0.007%

    No Known Activations