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

    Neuronpedia

    INDEX
    Explanations

    "%"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     incumb
    -0.08
     Communities
    -0.07
     yem
    -0.07
    Legal
    -0.07
     groundwork
    -0.07
     Managed
    -0.06
    Sites
    -0.06
    WriteBarrier
    -0.06
     grateful
    -0.06
    Γ
    -0.06
    POSITIVE LOGITS
    lere
    0.07
    .room
    0.06
     раді
    0.06
    subs
    0.06
     synth
    0.06
    hlen
    0.06
    setProperty
    0.06
     Mormon
    0.06
    最後
    0.05
     traction
    0.05
    Act Density 0.012%

    No Known Activations