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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tu
    -0.08
    .Home
    -0.07
     �
    -0.07
     nadzieję
    -0.07
    andez
    -0.07
    ($_
    -0.07
    ponsored
    -0.07
    ardash
    -0.07
    ント
    -0.07
    ユー
    -0.07
    POSITIVE LOGITS
     =======
    0.07
     antenn
    0.07
    .•
    0.06
    .Ag
    0.06
     pobli
    0.06
    ण
    0.06
    썻
    0.06
     <<↵
    0.06
     Commands
    0.06
     say
    0.06
    Act Density 0.014%

    No Known Activations