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

    Neuronpedia

    INDEX
    Explanations

    SQL schema definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    んじゃない
    0.45
     pessimistic
    0.41
     消
    0.41
     minifyEnabled
    0.40
     methodName
    0.40
     নও
    0.40
    ্ু
    0.39
     renderEncoder
    0.39
     डाउट्स
    0.39
     amplit
    0.39
    POSITIVE LOGITS
    alter
    0.68
    ALTER
    0.55
     Indexes
    0.55
     linking
    0.54
    relationship
    0.54
     alter
    0.53
     relationship
    0.52
     Alter
    0.52
     alters
    0.51
    linking
    0.50
    Act Density 0.007%

    No Known Activations