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

    Neuronpedia

    INDEX
    Explanations

    Connecting words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cot
    -0.06
    choice
    -0.06
    rightarrow
    -0.06
    ek
    -0.06
    bio
    -0.06
     باشید
    -0.06
     setUsername
    -0.06
     conversation
    -0.06
     GestureDetector
    -0.06
     проис
    -0.06
    POSITIVE LOGITS
     зелен
    0.07
     林
    0.07
     Masc
    0.07
    �
    0.06
     Pawn
    0.06
    �
    0.06
     tweets
    0.06
    .Base
    0.06
    ную
    0.06
    uem
    0.06
    Act Density 0.609%

    No Known Activations