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

    Neuronpedia

    INDEX
    Explanations

    documentation links

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ferd
    -0.07
    ou
    -0.07
    Zh
    -0.07
     sắt
    -0.07
    AEA
    -0.06
    ';';
    -0.06
     Jana
    -0.06
     ORD
    -0.06
    Р
    -0.06
     \'
    -0.06
    POSITIVE LOGITS
     Early
    0.07
    _HPP
    0.07
     kleine
    0.07
    bringing
    0.06
    >(*
    0.06
     Declarations
    0.06
    .Messages
    0.06
    _FUN
    0.06
    ystery
    0.06
    �
    0.06
    Act Density 0.011%

    No Known Activations