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

    Neuronpedia

    INDEX
    Explanations

    tree diagram components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    рованной
    0.44
    יו
    0.44
    8
    0.43
     인한
    0.42
    搭载
    0.42
    ᚖ
    0.40
    нную
    0.40
    an
    0.40
    ธอ
    0.40
    常规
    0.40
    POSITIVE LOGITS
     Muslims
    0.46
    }$,
    0.45
     Drugs
    0.44
     Controller
    0.44
     researched
    0.44
     Diz
    0.43
     Calcium
    0.43
     Determining
    0.43
     If
    0.42
     Synopsis
    0.42
    Act Density 0.000%

    No Known Activations