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

    Neuronpedia

    INDEX
    Explanations

    item

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    offer
    -0.07
    716
    -0.06
     GPA
    -0.06
    ashes
    -0.06
    add
    -0.06
    ";↵
    -0.06
    'Re
    -0.06
    Cluster
    -0.06
     consultations
    -0.06
    .compile
    -0.06
    POSITIVE LOGITS
    �
    0.07
    ลงท
    0.07
    .toObject
    0.07
     attribute
    0.06
     opatření
    0.06
     fatalError
    0.06
     tasks
    0.06
    现场
    0.06
    ]?
    0.06
     gön
    0.06
    Act Density 0.003%

    No Known Activations