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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Narrated
    -0.06
    iac
    -0.06
    Mur
    -0.06
    ัน
    -0.06
     плани
    -0.06
    .dataset
    -0.06
    واع
    -0.06
     perc
    -0.06
     Sacred
    -0.06
    _lst
    -0.06
    POSITIVE LOGITS
     parcels
    0.08
     течение
    0.08
     dünyada
    0.07
     containers
    0.06
     persever
    0.06
     thịt
    0.06
     흐
    0.06
     çocu
    0.06
    .RegisterType
    0.06
    Into
    0.06
    Act Density 0.055%

    No Known Activations