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

    Neuronpedia

    INDEX
    Explanations

    written text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    BUG
    -0.07
     actresses
    -0.07
    трен
    -0.07
    vault
    -0.07
    חוז
    -0.07
    𐤕
    -0.07
     trợ
    -0.07
     ()->
    -0.06
    剋
    -0.06
    ᖓ
    -0.06
    POSITIVE LOGITS
    reverse
    0.08
     mix
    0.08
    oader
    0.08
     Grim
    0.07
     WOW
    0.07
    -handle
    0.07
     [...
    0.07
     הרי
    0.07
     Ready
    0.07
     '.
    0.07
    Act Density 0.035%

    No Known Activations