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

    Neuronpedia

    INDEX
    Explanations

    calculate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Winner
    -0.07
     zad
    -0.06
    Page
    -0.06
     evapor
    -0.06
    ,y
    -0.06
    .namespace
    -0.06
    '>↵↵
    -0.06
     memory
    -0.06
     सव
    -0.06
     Sent
    -0.06
    POSITIVE LOGITS
    Calculate
    0.08
     responsibly
    0.08
    μ
    0.07
     excessive
    0.07
    Check
    0.07
     µ
    0.07
    activities
    0.07
     happening
    0.07
    ground
    0.07
    cessive
    0.07
    Act Density 0.006%

    No Known Activations