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

    Neuronpedia

    INDEX
    Explanations

    preparation, storing, validation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     spacerItem
    0.46
     صنعتی
    0.45
     internazionale
    0.45
     bukan
    0.44
     જગ
    0.44
     licences
    0.43
    Kob
    0.43
    colato
    0.42
     internazionali
    0.42
     międzynarod
    0.42
    POSITIVE LOGITS
    ",
    0.45
    reas
    0.45
    炎
    0.44
    acf
    0.44
    R
    0.44
    3
    0.43
    ires
    0.42
     pelvis
    0.42
    数
    0.42
    rea
    0.42
    Act Density 0.006%

    No Known Activations