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

    Neuronpedia

    INDEX
    Explanations

    total price, would respond, two legs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ettha
    1.24
    Usuarios
    1.24
    Workflow
    1.22
    <unused149>
    1.21
    Macrophages
    1.19
    <unused275>
    1.15
    Blockchain
    1.15
    Coconut
    1.14
    Usuario
    1.14
     Система
    1.14
    POSITIVE LOGITS
      
    1.16
     (
    1.06
    ,
    0.92
     ​​
    0.92
     and
    0.90
    <0xC2>
    0.89
     *
    0.88
    /
    0.86
    -
    0.84
     is
    0.83
    Act Density 6.090%

    No Known Activations