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

    Neuronpedia

    INDEX
    Explanations

    Counting and ordering

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     HOA
    -0.08
     PTO
    -0.08
    tof
    -0.08
     Il
    -0.07
     מל
    -0.07
     son
    -0.07
     furious
    -0.07
     multifunction
    -0.07
     moisturizing
    -0.07
     repairs
    -0.07
    POSITIVE LOGITS
    ailable
    0.09
    zag
    0.08
     spawn
    0.08
    elig
    0.08
    .Safe
    0.08
     debuted
    0.08
     चुन
    0.08
     standout
    0.07
     अनेक
    0.07
     Spill
    0.07
    Act Density 0.013%

    No Known Activations