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

    Neuronpedia

    INDEX
    Explanations

    filesystems or formatting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    itious
    -0.07
     Muslim
    -0.07
    拌
    -0.07
    should
    -0.07
    蛋白
    -0.07
    桹
    -0.06
     disappointment
    -0.06
    isa
    -0.06
    ivre
    -0.06
    ובש
    -0.06
    POSITIVE LOGITS
    ]};↵
    0.07
     Именно
    0.07
    Ranges
    0.07
     drains
    0.07
    ThreadId
    0.07
    🔆
    0.07
    큰
    0.07
    _exact
    0.07
    _SCHED
    0.07
    内幕
    0.07
    Act Density 0.015%

    No Known Activations