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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     covered
    -0.07
    orna
    -0.07
    ��
    -0.06
     UIS
    -0.06
    IOC
    -0.06
     Carnegie
    -0.06
    GenerationStrategy
    -0.06
     type
    -0.06
    _WE
    -0.06
    (IS
    -0.06
    POSITIVE LOGITS
    _CHAN
    0.07
     crown
    0.07
    (EFFECT
    0.06
     uprav
    0.06
     còn
    0.06
    Ap
    0.06
     rap
    0.06
     свой
    0.06
     	↵
    0.06
     histó
    0.06
    Act Density 0.026%

    No Known Activations