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

    Neuronpedia

    INDEX
    Explanations

    programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     finding
    -0.08
    akes
    -0.08
    stone
    -0.07
    .java
    -0.07
     Corinthians
    -0.07
    amientos
    -0.07
    醫療
    -0.07
    os
    -0.07
    🙅
    -0.07
    道具
    -0.07
    POSITIVE LOGITS
    ivot
    0.07
     Worldwide
    0.07
    pn
    0.07
    艳
    0.06
    幔
    0.06
     Trom
    0.06
     retreat
    0.06
    organizations
    0.06
     Any
    0.06
     role
    0.06
    Act Density 0.050%

    No Known Activations