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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    argon
    -0.07
     records
    -0.07
     Wizards
    -0.07
    URRENT
    -0.07
     archive
    -0.07
     ку
    -0.06
     columnist
    -0.06
    -end
    -0.06
    nosti
    -0.06
    060
    -0.06
    POSITIVE LOGITS
    .SetValue
    0.07
     Congratulations
    0.06
    出品者
    0.06
     boundary
    0.06
    .Null
    0.06
    "io
    0.06
    ’i
    0.06
    cpp
    0.06
    /testify
    0.06
    .nil
    0.06
    Act Density 0.014%

    No Known Activations