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
    Flex
    -0.07
    fabric
    -0.06
    ROID
    -0.06
    Retrieve
    -0.06
    ratio
    -0.06
    Field
    -0.06
    built
    -0.06
    ec
    -0.06
    Spec
    -0.06
    -vis
    -0.06
    POSITIVE LOGITS
     abruptly
    0.07
     nom
    0.06
     कर
    0.06
     Maduro
    0.06
    _chunks
    0.06
     uni
    0.06
     clean
    0.06
     Potential
    0.06
     BEN
    0.06
    ])){↵
    0.06
    Act Density 0.013%

    No Known Activations