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

    Neuronpedia

    INDEX
    Explanations

    mam, mammoth, mamta

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cad
    0.42
    суз
    0.41
    köy
    0.39
     cruz
    0.38
     declarat
    0.38
    craft
    0.38
     sinn
    0.37
    örung
    0.37
    kreuz
    0.36
    autical
    0.36
    POSITIVE LOGITS
     Mama
    0.48
    ons
    0.45
    Mama
    0.45
     Mammoth
    0.44
    Mamm
    0.43
     ममता
    0.43
    Mam
    0.43
     tortoise
    0.42
    ॉन
    0.42
    ONS
    0.41
    Act Density 0.001%

    No Known Activations