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

    Neuronpedia

    INDEX
    Explanations

    Rhode

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     freight
    -1.05
     Freight
    -0.87
    freight
    -0.69
    Freight
    -0.68
    InstrumentedTest
    -0.58
    etta
    -0.57
    execSQL
    -0.56
    ExecuteReader
    -0.53
     poème
    -0.52
    Gre
    -0.52
    POSITIVE LOGITS
     autorytatywna
    0.67
    łaszcza
    0.57
    segno
    0.56
    liner
    0.56
     يتيمه
    0.54
    alism
    0.54
    SequentialGroup
    0.54
    ally
    0.54
    onomía
    0.54
    ngOn
    0.52
    Act Density 0.009%

    No Known Activations