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

    Neuronpedia

    INDEX
    Explanations

    use

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cers
    -0.07
    _heads
    -0.07
    .freeze
    -0.07
     RSA
    -0.07
    VENTORY
    -0.06
    ជ
    -0.06
     помещения
    -0.06
    moth
    -0.06
    笸
    -0.06
     пре
    -0.06
    POSITIVE LOGITS
    _item
    0.07
    lógica
    0.07
    Playable
    0.07
     данным
    0.07
     ItemType
    0.07
     جميل
    0.07
    淡化
    0.07
     fopen
    0.06
    EEDED
    0.06
     secure
    0.06
    Act Density 0.026%

    No Known Activations