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

    Neuronpedia

    INDEX
    Explanations

    Оп

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     trough
    -0.06
     cooler
    -0.06
    xyz
    -0.06
    cade
    -0.06
    (bytes
    -0.06
    ,c
    -0.06
     anymore
    -0.06
     CDs
    -0.06
     sorrow
    -0.06
    =d
    -0.06
    POSITIVE LOGITS
     हम
    0.07
    vio
    0.07
     wishlist
    0.07
     {}↵↵
    0.06
    \.
    0.06
    _OP
    0.06
     dealloc
    0.06
    ��
    0.06
    _services
    0.06
    mind
    0.06
    Act Density 0.003%

    No Known Activations