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

    Neuronpedia

    INDEX
    Explanations

    yl

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    řila
    -0.07
    руп
    -0.07
     Martian
    -0.07
    filt
    -0.07
    ovie
    -0.06
     Setup
    -0.06
    bindung
    -0.06
    ULSE
    -0.06
     meille
    -0.06
     到
    -0.06
    POSITIVE LOGITS
     Kn
    0.07
    _ACTIVITY
    0.07
     collisions
    0.06
     των
    0.06
     Coins
    0.06
     inflater
    0.06
     Know
    0.06
     Style
    0.06
     onions
    0.06
    ..<
    0.06
    Act Density 0.001%

    No Known Activations