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

    Neuronpedia

    INDEX
    Explanations

    ms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     choir
    -0.07
     Setting
    -0.07
    (enum
    -0.07
     prediction
    -0.06
     committee
    -0.06
    .thread
    -0.06
     QUESTION
    -0.06
     credibility
    -0.06
    transition
    -0.06
    whatever
    -0.06
    POSITIVE LOGITS
     الجن
    0.06
     Behavioral
    0.06
     đào
    0.06
     snel
    0.06
    λλι
    0.06
    _plural
    0.06
    ักส
    0.06
    _APB
    0.06
     desper
    0.06
    otas
    0.06
    Act Density 0.001%

    No Known Activations