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

    Neuronpedia

    INDEX
    Explanations

    varied topics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     releases
    -0.07
     right
    -0.07
     bog
    -0.07
    akes
    -0.07
    '];?>"
    -0.07
     landed
    -0.06
     bare
    -0.06
     düşman
    -0.06
     SW
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    duto
    0.07
    .Predicate
    0.07
    .simpleButton
    0.06
    pection
    0.06
    標
    0.06
     належ
    0.06
    lenen
    0.06
     SharedModule
    0.06
    avatar
    0.06
    ategory
    0.06
    Act Density 0.161%

    No Known Activations