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

    Neuronpedia

    INDEX
    Explanations

    important caveats first

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    льная
    0.46
     sleeveless
    0.46
    ادیه
    0.45
     Minister
    0.45
     resort
    0.44
     Aut
    0.44
    ickou
    0.44
     Menteri
    0.43
    میری
    0.43
     Editor
    0.42
    POSITIVE LOGITS
     pollinators
    0.52
    its
    0.50
     mortgages
    0.49
    袮
    0.49
     rutas
    0.48
     odors
    0.47
    executions
    0.47
    asons
    0.46
    asts
    0.46
    🥤
    0.46
    Act Density 0.001%

    No Known Activations