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

    Neuronpedia

    INDEX
    Explanations

    sequences following symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    borderRadius
    0.39
     frequented
    0.39
    trif
    0.38
     promiscu
    0.38
     requirement
    0.38
     круп
    0.38
     tripartite
    0.37
    rnd
    0.37
     trif
    0.37
    OCA
    0.37
    POSITIVE LOGITS
     ഹ
    0.39
     Ре
    0.38
     Res
    0.38
     माइनस
    0.37
    Res
    0.37
     /**@
    0.37
     Ра
    0.37
     ор
    0.36
     Ros
    0.36
     Raum
    0.35
    Act Density 0.001%

    No Known Activations