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

    Neuronpedia

    INDEX
    Explanations

    except Exception as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PE
    0.75
    লাইট
    0.74
    ripcion
    0.71
    线
    0.69
    PES
    0.67
    lights
    0.66
    پ
    0.66
    ünkü
    0.65
    პ
    0.64
    飲み
    0.64
    POSITIVE LOGITS
     kn
    0.69
     Kn
    0.63
    kn
    0.59
     Ga
    0.58
    retch
    0.56
     looked
    0.56
     verg
    0.56
    jeff
    0.55
     quotations
    0.55
     Nod
    0.55
    Act Density 0.116%

    No Known Activations