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

    Neuronpedia

    INDEX
    Explanations

    He

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     implicit
    -0.07
     economics
    -0.07
     recip
    -0.07
     Fallout
    -0.07
     constantly
    -0.06
     interfere
    -0.06
    从
    -0.06
     Welch
    -0.06
    Canvas
    -0.06
     rays
    -0.06
    POSITIVE LOGITS
    He
    0.08
    “She
    0.07
    "He
    0.07
    '].'/
    0.07
     He
    0.07
    "She
    0.07
     styleUrls
    0.07
     HE
    0.06
    uter
    0.06
    HomeAs
    0.06
    Act Density 0.009%

    No Known Activations