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

    Neuronpedia

    INDEX
    Explanations

    .C

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ُل
    -0.07
     restricting
    -0.07
    WB
    -0.06
    �
    -0.06
    -0.06
     battalion
    -0.06
    丘
    -0.06
    MATCH
    -0.06
    amped
    -0.06
    流
    -0.06
    POSITIVE LOGITS
    ();

↵
    0.07
    shi
    0.07
     Arte
    0.07
    最新
    0.07
    _OVERFLOW
    0.06
    <any
    0.06
    _)↵
    0.06
     [[]
    0.06
    Roles
    0.06
    :'#
    0.06
    Act Density 0.001%

    No Known Activations