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

    Neuronpedia

    INDEX
    Explanations

    find

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dahl
    -0.07
     Merkel
    -0.07
     Ts
    -0.07
     AMS
    -0.07
     Edmonton
    -0.06
     Lebens
    -0.06
     Dé
    -0.06
     Vick
    -0.06
     Hamilton
    -0.06
     Ske
    -0.06
    POSITIVE LOGITS
     find
    0.10
    .sender
    0.08
    TOKEN
    0.07
     discovering
    0.07
    expl
    0.07
    -ring
    0.07
    っき
    0.07
    _players
    0.06
    stories
    0.06
    .handler
    0.06
    Act Density 0.037%

    No Known Activations