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

    Neuronpedia

    INDEX
    Explanations

    You can, as follows

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    นาะ
    1.12
    🔥🔥
    1.11
    어를
    1.10
    ricting
    1.09
    socketList
    1.09
     Nxe
    1.09
    瘠
    1.08
    ❤️❤️
    1.07
     پڑھیئے
    1.07
    앓
    1.07
    POSITIVE LOGITS
     znamen
    1.16
    टिक
    1.15
    rst
    1.15
    n
    1.13
    ै
    1.12
     prikaz
    1.12
    Durch
    1.07
    اد
    1.07
    Thông
    1.06
     taut
    1.06
    Act Density 0.000%

    No Known Activations