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

    Neuronpedia

    INDEX
    Explanations

    fer prefix, ferret, ferrous, fermentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ကြ
    0.47
     classifies
    0.45
    igns
    0.41
     threatens
    0.41
    嘬
    0.40
     CHAS
    0.40
    俞
    0.39
     isnt
    0.39
     чек
    0.39
    𒄷
    0.39
    POSITIVE LOGITS
     Fer
    0.57
     fer
    0.55
    Fer
    0.55
     Ferr
    0.55
    Ferr
    0.51
     ferr
    0.49
     FER
    0.47
     ferro
    0.47
     ferret
    0.45
    fer
    0.45
    Act Density 0.007%

    No Known Activations