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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rough
    -0.07
    AGMA
    -0.07
    Animation
    -0.07
    egr
    -0.07
    .level
    -0.07
     snippet
    -0.07
    太平洋
    -0.07
    超過
    -0.06
    Override
    -0.06
    .Block
    -0.06
    POSITIVE LOGITS
    cles
    0.08
     meals
    0.07
     Assembly
    0.07
     Reaction
    0.07
    ימון
    0.06
     CSC
    0.06
    пла
    0.06
    ecal
    0.06
    乒乓球
    0.06
    ὡ
    0.06
    Act Density 0.077%

    No Known Activations