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

    Neuronpedia

    INDEX
    Explanations

    /

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    toBeInTheDocument
    -0.07
     contradictions
    -0.07
    DOG
    -0.06
    우리
    -0.06
     setData
    -0.06
     McCabe
    -0.06
     एल
    -0.06
     kurul
    -0.06
     sharp
    -0.06
     restored
    -0.06
    POSITIVE LOGITS
     selfish
    0.06
    .AddModelError
    0.06
    ynch
    0.06
    (rep
    0.06
     dealloc
    0.06
     Assess
    0.06
     ORIGINAL
    0.06
    InstanceId
    0.06
    	ns
    0.06
    _UNDEF
    0.06
    Act Density 0.008%

    No Known Activations