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
     connectors
    -0.06
     bridges
    -0.06
    Watcher
    -0.06
     Twice
    -0.06
     amounts
    -0.06
     explanations
    -0.06
     wins
    -0.06
    consult
    -0.06
    gets
    -0.06
    	results
    -0.06
    POSITIVE LOGITS
     „
    0.07
     LA
    0.07
    (fabs
    0.06
     LSU
    0.06
    =:
    0.06
    ‐'
    0.06
     heavyweight
    0.06
    atsby
    0.06
     sido
    0.06
    (['
    0.06
    Act Density 0.047%

    No Known Activations