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

    Neuronpedia

    INDEX
    Explanations

    learning activities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    izational
    -0.07
    染
    -0.07
    Hands
    -0.06
    Radio
    -0.06
     Pink
    -0.06
     nuclei
    -0.06
    Hundreds
    -0.06
    DTO
    -0.06
    _hid
    -0.06
     기
    -0.06
    POSITIVE LOGITS
    なた
    0.07
    ालन
    0.06
     letras
    0.06
     в
    0.06
     ابراه
    0.06
     Pir
    0.06
    imachinery
    0.06
     літ
    0.06
    ли
    0.06
     ])
    0.05
    Act Density 0.053%

    No Known Activations