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

    Neuronpedia

    INDEX
    Explanations

    references

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    گ
    -0.08
     factorial
    -0.07
     Nation
    -0.07
     ]↵↵↵
    -0.07
    ({
    -0.07
    不存在
    -0.06
    .SystemColors
    -0.06
     Deleting
    -0.06
    ustral
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    _lvl
    0.08
    蟠
    0.07
     tavern
    0.07
     McCarthy
    0.07
    ersive
    0.07
    ﾛ
    0.07
    𝓊
    0.07
    olu
    0.07
    xis
    0.07
    굼
    0.07
    Act Density 0.004%

    No Known Activations