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

    Neuronpedia

    INDEX
    Explanations

    Dates in blog posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /tr
    -0.07
    वत
    -0.07
    .Pro
    -0.07
    CHIP
    -0.06
    /engine
    -0.06
    .we
    -0.06
    vä
    -0.06
    ,s
    -0.06
    ########################################################
    -0.06
     diğer
    -0.06
    POSITIVE LOGITS
     animation
    0.06
     fray
    0.06
     Treasury
    0.06
     ac
    0.06
     Kendrick
    0.06
     Warrior
    0.06
     metab
    0.06
    ειτουργ
    0.06
    encrypt
    0.05
     período
    0.05
    Act Density 0.026%

    No Known Activations