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

    Neuronpedia

    INDEX
    Explanations

    breaking down concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CE
    0.52
    lava
    0.46
     Medicina
    0.45
    CA
    0.45
     edificio
    0.44
     aplicado
    0.44
    INE
    0.43
    áfico
    0.43
     inteligencia
    0.43
     noroeste
    0.43
    POSITIVE LOGITS
    verständ
    0.52
     trial
    0.45
    氳
    0.45
     stealth
    0.44
    ሪ
    0.44
    のは
    0.44
     favorite
    0.44
    λα
    0.44
    ამო
    0.43
     intentional
    0.43
    Act Density 0.001%

    No Known Activations