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

    Neuronpedia

    INDEX
    Explanations

    availability/absorption

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Recovered
    -0.07
     Pipe
    -0.06
     Theodore
    -0.06
    	win
    -0.06
    Timeout
    -0.06
     OUT
    -0.06
     рас
    -0.06
    ду
    -0.06
     Reactive
    -0.06
     intermedi
    -0.06
    POSITIVE LOGITS
     ):↵↵
    0.06
    =L
    0.06
     Patch
    0.06
    parse
    0.06
    ="$(
    0.06
     formulation
    0.06
    validate
    0.06
    aggregate
    0.06
    ("../../
    0.06
     TArray
    0.06
    Act Density 0.029%

    No Known Activations