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

    Neuronpedia

    INDEX
    Explanations

    text describing recipes or scientific studies involving shrimp

    oai_token-act-pair · gemini-2.0-flash

    shrimp

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    agrad
    -0.51
    üte
    -0.50
    üten
    -0.50
    uki
    -0.47
     kính
    -0.45
     operator
    -0.44
     rând
    -0.44
    istungen
    -0.43
    ย์
    -0.43
     kuş
    -0.43
    POSITIVE LOGITS
    ագրություններ
    0.91
    StructEnd
    0.75
    parsedMessage
    0.70
    Jeografia
    0.69
    таратура
    0.69
     transfieras
    0.64
     незавершена
    0.64
     Normdatei
    0.64
     wireType
    0.62
    EndContext
    0.61
    Act Density 1.402%

    No Known Activations