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

    Neuronpedia

    INDEX
    Explanations

    recent years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝘭
    0.44
    𝘪
    0.42
    Bild
    0.38
    вание
    0.38
    튕
    0.37
    uous
    0.37
    вания
    0.37
    েনারেল
    0.37
    css
    0.36
    ատ
    0.36
    POSITIVE LOGITS
    م
    0.51
    ak
    0.48
     pacemaker
    0.48
     judges
    0.47
    砜
    0.47
     elephant
    0.47
     eTo
    0.47
     concentric
    0.47
    ਆਂ
    0.46
    anso
    0.46
    Act Density 0.010%

    No Known Activations