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

    Neuronpedia

    INDEX
    Explanations

    Text alignment in code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     
↵
↵
    -0.08
     &&
↵
    -0.08
    ]:
↵
    -0.08
    elt
    -0.08
    ]
↵
↵
    -0.08
    ТР
    -0.08
    ări
    -0.08
    （二
    -0.08
    _calls
    -0.08
     níveis
    -0.07
    POSITIVE LOGITS
     isticma
    0.08
     voorstelling
    0.08
     PQ
    0.07
    leanor
    0.07
    Mq
    0.07
     देकर
    0.07
     MSS
    0.07
     მეგობ
    0.07
     cement
    0.07
     दोस्त
    0.07
    Act Density 0.001%

    No Known Activations