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

    Neuronpedia

    INDEX
    Explanations

    I'll cover everything

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ymethyl
    0.21
     diatas
    0.20
    irin
    0.20
    vykor
    0.20
     innych
    0.19
    vál
    0.18
    endregion
    0.18
     अन्य
    0.18
    kgs
    0.18
    :**
    0.18
    POSITIVE LOGITS
    First
    0.21
     blogging
    0.21
    Part
    0.21
    this
    0.20
     Blogging
    0.20
    Because
    0.20
    分为
    0.20
     carnival
    0.20
    APK
    0.20
     we
    0.19
    Act Density 0.214%

    No Known Activations