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

    Neuronpedia

    INDEX
    Explanations

    punctuation / word "that"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     NavParams
    -0.07
    toThrow
    -0.07
     LORD
    -0.06
     Protocol
    -0.06
     DBG
    -0.06
     утвержд
    -0.06
    _package
    -0.06
     crosses
    -0.06
    Child
    -0.06
     :=
    -0.06
    POSITIVE LOGITS
    atin
    0.07
     GRAT
    0.06
    ,state
    0.06
     getInt
    0.06
     setEmail
    0.06
     stol
    0.06
    zig
    0.06
    ูรณ
    0.06
    andon
    0.06
     contin
    0.06
    Act Density 0.034%

    No Known Activations