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

    Neuronpedia

    INDEX
    Explanations

    odd

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fstream
    -0.08
    =args
    -0.08
     Marcel
    -0.08
    rient
    -0.08
     CONTROL
    -0.07
    Boost
    -0.07
    进入
    -0.07
    一個
    -0.07
    .exports
    -0.07
    winter
    -0.07
    POSITIVE LOGITS
     odds
    0.10
     odd
    0.10
    Odd
    0.09
     Odd
    0.08
    illi
    0.07
     DAY
    0.07
     �
    0.07
     Mend
    0.06
    857
    0.06
    ells
    0.06
    Act Density 0.004%

    No Known Activations