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

    Neuronpedia

    INDEX
    Explanations

    phrasal constructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     являются
    0.42
     flanking
    0.42
    ላሉ
    0.39
     artific
    0.38
     leve
    0.38
    trashItem
    0.38
    ரை
    0.38
     horned
    0.38
     مذہ
    0.38
     leveling
    0.37
    POSITIVE LOGITS
    ventyConfig
    0.51
     spoloč
    0.46
    INE
    0.45
    候
    0.44
    ៉ុ
    0.42
     CHF
    0.42
    不容易
    0.42
     PCP
    0.42
     Prosperity
    0.42
    麵
    0.42
    Act Density 0.008%

    No Known Activations