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

    Neuronpedia

    INDEX
    Explanations

    factual claim or opinion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ৭০
    0.40
     volutpat
    0.39
    imin
    0.39
    achs
    0.37
    Woods
    0.37
     Woods
    0.37
     yi
    0.37
    xlab
    0.37
     ද
    0.36
    dden
    0.36
    POSITIVE LOGITS
     Gladi
    0.41
    ಲಾ
    0.40
    étation
    0.39
    フォロー
    0.39
    ছুর
    0.39
     testimonies
    0.38
    ⤦
    0.38
     SBOM
    0.37
    ರಿನ
    0.37
    LogProfile
    0.37
    Act Density 0.000%

    No Known Activations