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

    Neuronpedia

    INDEX
    Explanations

    work experience

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ernational
    -0.07
    )?
    -0.07
    ,’”
    -0.07
     Indonesia
    -0.06
    BD
    -0.06
    clave
    -0.06
    降临
    -0.06
     مدريد
    -0.06
    akter
    -0.06
    ,NULL
    -0.06
    POSITIVE LOGITS
     Dare
    0.08
    .FromResult
    0.07
     Able
    0.07
    의
    0.07
    .finished
    0.07
    �
    0.07
    cite
    0.07
    .dm
    0.07
    ably
    0.07
     Smoke
    0.06
    Act Density 0.041%

    No Known Activations