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

    Neuronpedia

    INDEX
    Explanations

    question-answer context

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kolem
    -0.07
     meget
    -0.07
    activities
    -0.06
    від
    -0.06
     чт
    -0.06
     Halifax
    -0.06
    _addresses
    -0.06
     अब
    -0.06
     RTE
    -0.06
    Condition
    -0.06
    POSITIVE LOGITS
    creds
    0.06
    vu
    0.06
     Bound
    0.06
    (avg
    0.06
    πή
    0.06
    Frames
    0.05
    ्पत
    0.05
    とな
    0.05
     Argument
    0.05
    .resp
    0.05
    Act Density 0.163%

    No Known Activations