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

    Neuronpedia

    INDEX
    Explanations

    ruins

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .gamma
    -0.07
    archical
    -0.07
    [MAXN
    -0.06
    $date
    -0.06
     buflen
    -0.06
    (Service
    -0.06
    consult
    -0.06
     playful
    -0.06
    ूस
    -0.06
    CONNECT
    -0.06
    POSITIVE LOGITS
     ruins
    0.10
    .face
    0.07
     wreckage
    0.07
     impeachment
    0.07
     ruin
    0.07
     Wings
    0.07
     ashes
    0.06
     remains
    0.06
     wastewater
    0.06
    848
    0.06
    Act Density 0.008%

    No Known Activations