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

    Neuronpedia

    INDEX
    Explanations

    demographic categories and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    吋
    1.63
    Veja
    1.60
    ٠
    1.56
    Noir
    1.45
    ना
    1.45
    𝗇
    1.44
    refund
    1.40
     épa
    1.40
    hero
    1.40
    end
    1.36
    POSITIVE LOGITS
    k
    1.44
    e
    1.42
     byteArray
    1.42
    kari
    1.36
    LookAndFeels
    1.36
     AppComponent
    1.29
    aç
    1.28
    гістра
    1.26
     verdana
    1.26
    σίας
    1.25
    Act Density 0.000%

    No Known Activations