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

    Neuronpedia

    INDEX
    Explanations

    should

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    indered
    -0.06
    ).'
    -0.06
     руками
    -0.06
    dfs
    -0.06
    "/
    -0.06
     unlaw
    -0.06
    уму
    -0.06
     北京
    -0.06
     SID
    -0.06
     plentiful
    -0.06
    POSITIVE LOGITS
     participation
    0.07
     provider
    0.07
     Participation
    0.07
    -v
    0.06
     scientist
    0.06
    Inside
    0.06
    istic
    0.06
    amoto
    0.06
    .stdin
    0.06
     sexism
    0.06
    Act Density 0.003%

    No Known Activations