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

    Neuronpedia

    INDEX
    Explanations

    detail improves outcome

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    香
    -0.07
    Gun
    -0.07
    .Map
    -0.06
    Detect
    -0.06
     Detect
    -0.06
    _tags
    -0.06
    Processor
    -0.06
     IOException
    -0.06
     whiskey
    -0.06
     descendants
    -0.06
    POSITIVE LOGITS
    =B
    0.08
    ��
    0.07
    =b
    0.07
     descriptive
    0.07
     сб
    0.06
    ительное
    0.06
    �
    0.06
     ejaculation
    0.06
    :b
    0.06
     permutations
    0.06
    Act Density 0.012%

    No Known Activations