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

    Neuronpedia

    INDEX
    Explanations

    expense

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hepsi
    -0.07
     Ros
    -0.06
     Orient
    -0.06
    .room
    -0.06
    Fallback
    -0.06
     Technique
    -0.06
     Hass
    -0.06
     Libyan
    -0.06
     рус
    -0.06
     odd
    -0.06
    POSITIVE LOGITS
    няют
    0.08
    μή
    0.07
     спис
    0.07
     continents
    0.07
    \xd
    0.07
     confirming
    0.07
     gli
    0.06
    .Product
    0.06
    (avg
    0.06
    ）。↵
    0.06
    Act Density 0.014%

    No Known Activations