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

    Neuronpedia

    INDEX
    Explanations

    phone number 4357

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ade
    0.73
    ini
    0.68
    inda
    0.67
    avin
    0.66
    ac
    0.64
    ik
    0.63
    adip
    0.63
    assic
    0.61
    ite
    0.61
     Haunted
    0.61
    POSITIVE LOGITS
     implementations
    0.59
     homomorphisms
    0.59
    ەل
    0.55
     polymorphisms
    0.52
    รุ่น
    0.52
     keine
    0.51
     квартира
    0.51
     fondness
    0.51
    рованием
    0.49
     работать
    0.49
    Act Density 0.013%

    No Known Activations