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

    Neuronpedia

    INDEX
    Explanations

    code files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mez
    -0.07
     Matte
    -0.07
     Κα
    -0.07
     Hammer
    -0.07
    (bl
    -0.06
    abus
    -0.06
     cunning
    -0.06
     gradu
    -0.06
     토
    -0.06
    гл
    -0.06
    POSITIVE LOGITS
    หร
    0.07
     світу
    0.06
    Serialization
    0.06
     документів
    0.06
    <tbody
    0.06
    _constraint
    0.06
     UIApplication
    0.06
    [first
    0.06
    objectManager
    0.06
    .pl
    0.05
    Act Density 0.008%

    No Known Activations