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

    Neuronpedia

    INDEX
    Explanations

    changes names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ༨
    0.49
    ௐ
    0.47
    ༥
    0.47
    ாந்து
    0.46
    いただけ
    0.46
    いは
    0.45
     aclarar
    0.45
    碓
    0.44
    ческие
    0.44
     некоторые
    0.44
    POSITIVE LOGITS
     sobri
    0.51
     team
    0.50
     wonderland
    0.47
     kidn
    0.45
     dessert
    0.45
     Hunters
    0.45
    ideen
    0.45
     ER
    0.44
     vastly
    0.44
     അടുത്ത
    0.44
    Act Density 0.001%

    No Known Activations