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

    Neuronpedia

    INDEX
    Explanations

    length

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    евого
    -0.07
     ZX
    -0.07
     Cab
    -0.06
    409
    -0.06
     apex
    -0.06
     Ferr
    -0.06
    ीए
    -0.06
     ση
    -0.06
     cracks
    -0.06
     extractor
    -0.06
    POSITIVE LOGITS
    '],
    0.07
     которого
    0.06
     handic
    0.06
     FIRST
    0.06
     outstanding
    0.06
    "],
    0.06
    .Assertions
    0.06
     �
    0.06
    ]‏
    0.06
    .respond
    0.05
    Act Density 0.014%

    No Known Activations