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

    Neuronpedia

    INDEX
    Explanations

    various methods focus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    arima
    0.44
     갔
    0.38
    ermodel
    0.38
    alho
    0.37
    lication
    0.36
    语法
    0.36
     aceptar
    0.36
     eût
    0.36
    浏览器
    0.36
    样例
    0.35
    POSITIVE LOGITS
    各種
    0.54
     çeşitli
    0.53
    Various
    0.52
     various
    0.49
     focus
    0.48
    কিছু
    0.46
     몇
    0.46
     berbagai
    0.46
     বেশিরভাগ
    0.46
     fokus
    0.46
    Act Density 0.619%

    No Known Activations