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

    Neuronpedia

    INDEX
    Explanations

    words with 'Mon' prefix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    in
    0.64
    alary
    0.52
    𝐦
    0.47
    inį
    0.46
    andro
    0.45
    inizi
    0.43
    atively
    0.42
    embers
    0.42
    inati
    0.41
    علم
    0.41
    POSITIVE LOGITS
     MON
    0.98
     mon
    0.96
     Mon
    0.88
     mono
    0.77
     моно
    0.76
    Mon
    0.75
     monop
    0.75
     モン
    0.70
     monoc
    0.69
     Mono
    0.66
    Act Density 0.021%

    No Known Activations