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

    Neuronpedia

    INDEX
    Explanations

    What I *Can* Do

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    l
    1.80
    ll
    1.77
    ل
    1.77
    ar
    1.68
    ik
    1.65
    er
    1.57
    es
    1.54
    िक
    1.53
    rr
    1.53
    n
    1.52
    POSITIVE LOGITS
     libres
    1.60
     maisons
    1.55
     cemeteries
    1.47
     mobiles
    1.46
     novelists
    1.46
     kojima
    1.45
     periodicals
    1.42
     monopolies
    1.40
     projectiles
    1.38
     механи
    1.36
    Act Density 0.084%

    No Known Activations