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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :numel
    -0.07
    ODE
    -0.07
     racked
    -0.07
    融资
    -0.07
    追踪
    -0.07
    锑
    -0.07
    .Azure
    -0.07
    솎
    -0.06
    溞
    -0.06
    Neill
    -0.06
    POSITIVE LOGITS
     ku
    0.07
     kad
    0.07
    club
    0.07
    律师事务
    0.07
    شاش
    0.07
     und
    0.07
    _package
    0.06
    ependency
    0.06
    ::
    0.06
    處理
    0.06
    Act Density 0.067%

    No Known Activations