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

    Neuronpedia

    INDEX
    Explanations

    names and places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    可能
    0.25
     choke
    0.23
     Keychain
    0.21
     మీరు
    0.21
    可以
    0.21
     follicles
    0.21
     dilute
    0.20
     zippers
    0.20
     granola
    0.20
     calorie
    0.20
    POSITIVE LOGITS
    had
    0.26
    ançois
    0.23
     González
    0.21
     and
    0.21
     Alexander
    0.20
    ían
    0.20
     Messrs
    0.20
    ías
    0.19
    assin
    0.19
    bert
    0.19
    Act Density 0.095%

    No Known Activations