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

    Neuronpedia

    INDEX
    Explanations

    seems

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     collectiv
    -0.08
     अपनी
    -0.07
     requirements
    -0.07
     faudra
    -0.07
     પોતાની
    -0.07
     પાસે
    -0.07
     finer
    -0.07
     विभिन्न
    -0.07
     추가
    -0.07
     अपने
    -0.07
    POSITIVE LOGITS
     trivial
    0.36
     triv
    0.24
     too
    0.24
     слишком
    0.22
     straightforward
    0.21
     terlalu
    0.21
    too
    0.20
     ridiculously
    0.20
     demasiado
    0.20
     Too
    0.20
    Act Density 0.092%

    No Known Activations