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

    Neuronpedia

    INDEX
    Explanations

    past states or actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Nineteenth
    0.43
    bg
    0.43
     morales
    0.42
     McCormick
    0.40
     prostitution
    0.39
    bot
    0.38
     doh
    0.38
     arco
    0.38
     sart
    0.37
     spook
    0.37
    POSITIVE LOGITS
    SetStr
    0.38
    inputSet
    0.38
    朖
    0.38
    仓
    0.37
    पीएफ
    0.37
     //-
    0.37
     нередко
    0.37
    酽
    0.36
    傈
    0.36
    ppers
    0.35
    Act Density 0.004%

    No Known Activations