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

    Neuronpedia

    INDEX
    Explanations

    React, migrations, pipeline, routes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     accountNumber
    0.31
     imageUrl
    0.30
    steppe
    0.30
    publicKey
    0.29
     ಮಾಹಿತಿ
    0.29
    ڈنگ
    0.29
     nDims
    0.29
     umjet
    0.29
     săptăm
    0.29
    imageUrl
    0.29
    POSITIVE LOGITS
     However
    0.37
     here
    0.35
     but
    0.35
    but
    0.35
     however
    0.33
     briefly
    0.33
     Briefly
    0.32
     uncomment
    0.31
     But
    0.31
     don
    0.31
    Act Density 0.000%

    No Known Activations