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

    Neuronpedia

    INDEX
    Explanations

    butter followed by food item

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     puro
    0.40
    cata
    0.39
     penny
    0.37
    penny
    0.37
     techo
    0.36
    Penny
    0.36
     wel
    0.36
     Penny
    0.36
     sacks
    0.36
    ßen
    0.35
    POSITIVE LOGITS
    issuer
    0.42
    含量
    0.39
    appList
    0.39
    ovač
    0.39
    issement
    0.37
     плав
    0.37
    㳑
    0.36
     capitalize
    0.36
     fid
    0.35
    도를
    0.35
    Act Density 0.004%

    No Known Activations