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

    Neuronpedia

    INDEX
    Explanations

    variety of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Taq
    0.92
    modification
    0.87
    Isl
    0.85
     programmi
    0.83
    ide
    0.83
    ilm
    0.83
    ______________
    0.81
    pla
    0.79
    Shr
    0.79
    Tel
    0.76
    POSITIVE LOGITS
    const
    1.75
     const
    1.45
     Clément
    1.19
     Const
    1.15
     Barcelona
    1.14
     let
    1.13
     Carson
    1.12
     async
    1.11
    console
    1.09
     Conor
    1.09
    Act Density 0.331%

    No Known Activations