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

    Neuronpedia

    INDEX
    Explanations

    MLOps, Securities, Protocol, Nation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     вести
    0.36
    ías
    0.36
    Denied
    0.35
    ﺓ
    0.35
    বঙ্গে
    0.35
     어느
    0.34
    馁
    0.34
     расс
    0.33
    Sexo
    0.33
    ியுள்ள
    0.33
    POSITIVE LOGITS
     M
    0.53
     MND
    0.52
     Madness
    0.50
     mayhem
    0.50
     MT
    0.50
     MN
    0.48
     MS
    0.47
     MH
    0.47
     MW
    0.47
     madness
    0.46
    Act Density 0.113%

    No Known Activations