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

    Neuronpedia

    INDEX
    Explanations

    dp

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >//
    -0.06
     pizzas
    -0.06
     갈
    -0.06
    InChildren
    -0.06
     slain
    -0.06
    。，
    -0.06
    出版社
    -0.06
     mdb
    -0.06
    ับม
    -0.06
     있는
    -0.06
    POSITIVE LOGITS
     P
    0.07
    Waiting
    0.07
     S
    0.06
    ーロ
    0.06
    choose
    0.06
     K
    0.06
     Якщо
    0.06
     "+"
    0.06
    hat
    0.06
    žit
    0.06
    Act Density 0.001%

    No Known Activations