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

    Neuronpedia

    INDEX
    Explanations

    hilarious

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Twist
    -0.07
    Services
    -0.06
    ский
    -0.06
     سنة
    -0.06
     马
    -0.06
    哪
    -0.06
    іх
    -0.06
    placing
    -0.06
     Dex
    -0.06
     thác
    -0.06
    POSITIVE LOGITS
    redd
    0.07
     basit
    0.07
    Assertions
    0.06
    út
    0.06
     instances
    0.06
     res
    0.06
    _UNDER
    0.06
     viagra
    0.06
    lando
    0.06
     Leonard
    0.06
    Act Density 0.015%

    No Known Activations