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

    Neuronpedia

    INDEX
    Explanations

    avoidselective foreign terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :
    0.59
     de
    0.58
     remembers
    0.50
     Adams
    0.48
     Structures
    0.48
     menc
    0.48
     (`
    0.48
     Beers
    0.47
     Things
    0.47
     Green
    0.46
    POSITIVE LOGITS
    ⟣
    0.56
     ferrugineux
    0.51
    ബന്ധ
    0.51
    ലീസ്
    0.49
     rufo
    0.49
    𝔯
    0.49
     pédicule
    0.49
    会社
    0.48
     ritorno
    0.47
     conflitto
    0.47
    Act Density 0.000%

    No Known Activations