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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "c
    -0.06
    IGO
    -0.06
    ,c
    -0.06
     сколько
    -0.06
     dov
    -0.06
    ИТ
    -0.06
    utton
    -0.06
    ussels
    -0.06
     EF
    -0.06
     وفي
    -0.06
    POSITIVE LOGITS
     diagrams
    0.08
     physically
    0.07
    _channels
    0.07
    lásil
    0.07
    �
    0.06
    $username
    0.06
     System
    0.06
     guard
    0.06
     ∈
    0.06
    060
    0.06
    Act Density 0.000%

    No Known Activations