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

    Neuronpedia

    INDEX
    Explanations

    listing specific items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    intention
    0.46
    p
    0.46
    ある
    0.45
    o
    0.45
    prepared
    0.44
    person
    0.44
     যার
    0.44
    patient
    0.44
    pm
    0.43
    projectName
    0.43
    POSITIVE LOGITS
     recuperación
    0.55
     güven
    0.54
     desblo
    0.54
     câteva
    0.52
     dört
    0.52
     três
    0.51
     néhány
    0.51
     navide
    0.51
     katk
    0.50
     meningkatkan
    0.49
    Act Density 0.001%

    No Known Activations