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

    Neuronpedia

    INDEX
    Explanations

    "The" followed by specific names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     иг
    0.76
     née
    0.75
    IN
    0.75
     ο
    0.74
     nee
    0.72
     alf
    0.69
     dehors
    0.66
    TIP
    0.66
     Where
    0.66
     aka
    0.65
    POSITIVE LOGITS
    atrical
    1.41
    odore
    1.29
    odora
    1.28
    oretically
    1.16
    orems
    1.14
    matic
    1.11
     Hague
    1.11
    ophilus
    1.09
    matics
    1.08
    atres
    1.08
    Act Density 0.148%

    No Known Activations