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

    Neuronpedia

    INDEX
    Explanations

    24

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    动物
    -0.07
    服务
    -0.07
    üne
    -0.07
    INCLUDED
    -0.07
     wel
    -0.07
    ác
    -0.06
     Grants
    -0.06
    арат
    -0.06
     září
    -0.06
    φή
    -0.06
    POSITIVE LOGITS
    (clone
    0.06
     exig
    0.06
    300
    0.06
     autoplay
    0.06
    uring
    0.06
    .CONTENT
    0.06
     Milf
    0.06
     perverse
    0.06
     ">↵
    0.06
    uning
    0.06
    Act Density 0.009%

    No Known Activations