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

    Neuronpedia

    INDEX
    Explanations

    Non-English

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     task
    -0.07
    tos
    -0.07
    .config
    -0.07
     amino
    -0.06
     çoğu
    -0.06
     multif
    -0.06
    自贸
    -0.06
    .setViewportView
    -0.06
    脆弱
    -0.06
    匠
    -0.06
    POSITIVE LOGITS
    穜
    0.07
    他又
    0.07
    后来
    0.07
     Evaluate
    0.07
    _booking
    0.07
    ])));↵
    0.06
     komment
    0.06
     Harvey
    0.06
    orate
    0.06
    石家
    0.06
    Act Density 0.115%

    No Known Activations