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

    Neuronpedia

    INDEX
    Explanations

    foreign words/code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    protocol
    -0.08
    _pool
    -0.06
    /layouts
    -0.06
     Parks
    -0.06
    <"
    -0.06
    _latency
    -0.06
    (E
    -0.06
    ette
    -0.06
    95
    -0.06
    Methods
    -0.06
    POSITIVE LOGITS
    董事
    0.07
     Ки
    0.07
     uten
    0.07
     заклад
    0.07
     바라
    0.07
     Panama
    0.07
    .AddTransient
    0.07
    @PostMapping
    0.07
    .tokens
    0.06
     mono
    0.06
    Act Density 0.010%

    No Known Activations